Changed HyperParameters Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:348118097b397f0686223be14f667e18ac57a0d2cba996b8068f8c52784f83c0
+oid sha256:390c8895a186c0156463bcfd36ea8c804709938a6edc9a1f98cbaeb754c045f3
 size 650646

SnowballTarget/SnowballTarget-1599976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105a95fcdab0a8c98123e9aae57d1ae0d6a2650d742a1c0ee118129221fcfe4b
+size 650646

SnowballTarget/SnowballTarget-1599976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c0870ac299fc526fb8264a68581392497cfae3bb4c921c72e6eddc64946e47
+size 3850705

SnowballTarget/SnowballTarget-1649992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc3de457d7d8c52afc424abb6e372ce0a3c26500238372ded4bc3115fe7a596
+size 650646

SnowballTarget/SnowballTarget-1649992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46101c1146ac879b7b4d3d88e89ca894bd19f42c66678941b9cbe871b1e8e9d5
+size 3850705

SnowballTarget/SnowballTarget-1699936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f8cbc54773ad15042f1718018934e28a080c702b1836461846405b4afa0708d
+size 650646

SnowballTarget/SnowballTarget-1699936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dedfd76e139d961b3398a682ebe727ad7993886808a999e0cef424be4e29a179
+size 3850705

SnowballTarget/SnowballTarget-1749960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94a7866f208fefd1f52d800d2edd300e17912d187122bc47d37cdece2cfcc55
+size 650646

SnowballTarget/SnowballTarget-1749960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7976bbdb79eb333dad5aad584eaa3e13821f411e67d0db0033b09be19c81c6e5
+size 3850705

SnowballTarget/SnowballTarget-1799984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e27dd28ee59a32cf0862c97f36e0c406a8aeb3812c7287f1baac73db4a01f9f
+size 650646

SnowballTarget/SnowballTarget-1799984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5c5fe59cfbad9dafb23ecdc451e16c2f56c9afd597d31f724a41fce26fa000
+size 3850705

SnowballTarget/SnowballTarget-1849984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b930aa08dc4b971e5838d54b3c01640b63199c0cce3acb216ba597a509b0de2
+size 650646

SnowballTarget/SnowballTarget-1849984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9177f9d685b332710400f190b3a531435d2c6279a8a9b712e33116a1c7920129
+size 3850705

SnowballTarget/SnowballTarget-1899944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bcfd80ae5b4e4de6c7367e6216cba6bdeb5bb493e8635f2106f3337907b6f2f
+size 650646

SnowballTarget/SnowballTarget-1899944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b43144ee506d08da9bf00d13062197da497fc979a7b6a14118cea60a953c65
+size 3850705

SnowballTarget/SnowballTarget-1949968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f528b24bc65161ce83c341707731e0d2a3656ad94c38633c3973bf1f30589a74
+size 650646

SnowballTarget/SnowballTarget-1949968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a11eb6a29b432f034a864d3fa0e66d32f8b94eff12b3ece7bae2b6e8f454c1
+size 3850705

SnowballTarget/SnowballTarget-1999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390c8895a186c0156463bcfd36ea8c804709938a6edc9a1f98cbaeb754c045f3
+size 650646

SnowballTarget/SnowballTarget-1999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40649a28ab5b929442f5197306c1c726798eb592046af3a43db565d5075ccf41
+size 3850705

SnowballTarget/SnowballTarget-2000504.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390c8895a186c0156463bcfd36ea8c804709938a6edc9a1f98cbaeb754c045f3
+size 650646

SnowballTarget/SnowballTarget-2000504.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586c86918dd1d16fc4fe4ea3daffc4361d84fa3ac97c1631bd56b2e90a87ba1a
+size 3850705

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb350d7fb4ec20139ff83c77dc67d253943fb75ecfd2080149a1307d4214441
+oid sha256:ced02b0e57ab123d83909078c8eb7e9759b59ccf67ff9ede7af959bf75a5c164
 size 3849717

SnowballTarget/events.out.tfevents.1756744183.hungchan-Precision-7560.15823.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b7e7d6bacee5e8f225174f961fb37a0d312b0f0c09935629ab3e0eda91f07f3
+size 184485

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 1024, "buffer_size": 10240, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 1024, "buffer_size": 10240, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -9,7 +9,7 @@ behaviors:
       beta: 0.01
       epsilon: 0.2
       lambd: 0.95
-      num_epoch: 3
+      num_epoch: 5
       shared_critic: false
       learning_rate_schedule: linear
       beta_schedule: linear
@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 200000
+    max_steps: 2000000
     time_horizon: 64
     summary_freq: 10000
     threaded: false
@@ -66,7 +66,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTarget2
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/media/hungchan/Storage/Works/xai/X AI/Code/Hugging Face RL/5. U
 Mono config path = '/media/hungchan/Storage/Works/xai/X AI/Code/Hugging Face RL/5. Unity ML-agent/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /home/hungchan/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /home/hungchan/.config/unity3d/Hugging Face/SnowballTarget
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /media/hungchan/Storage/Works/xai/X AI/Code/Hugging Face RL/5. Unity ML-agent/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -14,7 +11,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.053 seconds
+- Completed reload, in  0.062 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -25,7 +22,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.514438 ms
+UnloadTime: 0.426896 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 8 worker threads for Enlighten.
@@ -33,7 +30,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 53650 frames, [16.0 KB-32.0 KB]: 909 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -219,19 +216,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 37
+  Peak main deferred allocation count 40
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 13187 frames, [8.0 MB-16.0 MB]: 27610 frames, [16.0 MB-32.0 MB]: 13763 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 6.8 MB
+      Peak Block count 2
+      Peak Allocated memory 24.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 54560 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.6 MB
@@ -263,13 +260,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4045 frames, [64.0 KB-128.0 KB]: 1413 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 51576 frames, [64.0 KB-128.0 KB]: 2984 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 66.8 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 54560 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -281,13 +278,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5458 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 54560 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 54559 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -299,13 +296,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5458 frames
+      Peak usage frame count: [0-1.0 KB]: 54560 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 54560 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,213 +2,213 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 2.008164882659912,
-            "min": 2.008164882659912,
-            "max": 2.890336751937866,
-            "count": 20
+            "value": 0.7899582386016846,
+            "min": 0.7675452828407288,
+            "max": 2.8903439044952393,
+            "count": 200
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 19085.599609375,
-            "min": 19085.599609375,
-            "max": 29620.40234375,
-            "count": 20
+            "value": 8133.41015625,
+            "min": 7294.75048828125,
+            "max": 29570.138671875,
+            "count": 200
         },
         "SnowballTarget.Step.mean": {
-            "value": 199984.0,
+            "value": 1999992.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 1999992.0,
+            "count": 200
         },
         "SnowballTarget.Step.sum": {
-            "value": 199984.0,
+            "value": 1999992.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 1999992.0,
+            "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 5.566380023956299,
-            "min": 0.042696863412857056,
-            "max": 5.566380023956299,
-            "count": 20
+            "value": 14.199864387512207,
+            "min": -0.09513217210769653,
+            "max": 14.263813972473145,
+            "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1085.444091796875,
-            "min": 8.283191680908203,
-            "max": 1085.444091796875,
-            "count": 20
+            "value": 2910.97216796875,
+            "min": -18.45564079284668,
+            "max": 2924.081787109375,
+            "count": 200
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 20
+            "count": 200
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 8756.0,
+            "value": 10945.0,
             "min": 8756.0,
             "max": 10945.0,
-            "count": 20
+            "count": 200
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 14.522727272727273,
-            "min": 2.6136363636363638,
-            "max": 14.927272727272728,
-            "count": 20
+            "value": 27.90909090909091,
+            "min": 2.6363636363636362,
+            "max": 28.386363636363637,
+            "count": 200
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 639.0,
-            "min": 115.0,
-            "max": 821.0,
-            "count": 20
+            "value": 1535.0,
+            "min": 116.0,
+            "max": 1545.0,
+            "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 14.522727272727273,
-            "min": 2.6136363636363638,
-            "max": 14.927272727272728,
-            "count": 20
+            "value": 27.90909090909091,
+            "min": 2.6363636363636362,
+            "max": 28.386363636363637,
+            "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 639.0,
-            "min": 115.0,
-            "max": 821.0,
-            "count": 20
+            "value": 1535.0,
+            "min": 116.0,
+            "max": 1545.0,
+            "count": 200
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 200
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 200
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.020801379935195048,
-            "min": 0.01685354337096214,
-            "max": 0.029999618922981124,
-            "count": 19
+            "value": 0.023605609668884427,
+            "min": 0.015988392693398055,
+            "max": 0.029666174179874362,
+            "count": 191
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.020801379935195048,
-            "min": 0.01685354337096214,
-            "max": 0.029999618922981124,
-            "count": 19
+            "value": 0.023605609668884427,
+            "min": 0.015988392693398055,
+            "max": 0.029666174179874362,
+            "count": 191
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.355442476272583,
-            "min": 0.09278392195701599,
-            "max": 0.3592230121294657,
-            "count": 19
+            "value": 0.15311876356601714,
+            "min": 0.0945033897459507,
+            "max": 0.3203707575798035,
+            "count": 191
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.355442476272583,
-            "min": 0.09278392195701599,
-            "max": 0.3592230121294657,
-            "count": 19
+            "value": 0.15311876356601714,
+            "min": 0.0945033897459507,
+            "max": 0.3203707575798035,
+            "count": 191
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 1.9440993520000114e-06,
-            "min": 1.9440993520000114e-06,
-            "max": 0.00028363200545599993,
-            "count": 19
+            "value": 5.844998051999849e-07,
+            "min": 5.844998051999849e-07,
+            "max": 0.0002983632005456,
+            "count": 191
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 1.9440993520000114e-06,
-            "min": 1.9440993520000114e-06,
-            "max": 0.00028363200545599993,
-            "count": 19
+            "value": 5.844998051999849e-07,
+            "min": 5.844998051999849e-07,
+            "max": 0.0002983632005456,
+            "count": 191
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10064800000000003,
-            "min": 0.10064800000000003,
-            "max": 0.19454399999999994,
-            "count": 19
+            "value": 0.1001948,
+            "min": 0.1001948,
+            "max": 0.1994544,
+            "count": 191
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.10064800000000003,
-            "min": 0.10064800000000003,
-            "max": 0.19454399999999994,
-            "count": 19
+            "value": 0.1001948,
+            "min": 0.1001948,
+            "max": 0.1994544,
+            "count": 191
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 7.473520000000039e-05,
-            "min": 7.473520000000039e-05,
-            "max": 0.009454945599999997,
-            "count": 19
+            "value": 2.94605199999995e-05,
+            "min": 2.94605199999995e-05,
+            "max": 0.00994549456,
+            "count": 191
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 7.473520000000039e-05,
-            "min": 7.473520000000039e-05,
-            "max": 0.009454945599999997,
-            "count": 19
+            "value": 2.94605199999995e-05,
+            "min": 2.94605199999995e-05,
+            "max": 0.00994549456,
+            "count": 191
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1756743646",
+        "start_time_seconds": "1756744182",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/home/hungchan/miniconda3/envs/rl_31012/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/home/hungchan/miniconda3/envs/rl_31012/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1756743833"
+        "end_time_seconds": "1756746217"
     },
-    "total": 186.97781900200016,
+    "total": 2034.945576685,
     "count": 1,
-    "self": 0.21862168200004817,
+    "self": 0.22280772400017668,
     "children": {
         "run_training.setup": {
-            "total": 0.013576254000099652,
+            "total": 0.014937456999859933,
             "count": 1,
-            "self": 0.013576254000099652
+            "self": 0.014937456999859933
         },
         "TrainerController.start_learning": {
-            "total": 186.745621066,
+            "total": 2034.707831504,
             "count": 1,
-            "self": 0.22402318901185936,
+            "self": 2.090146202893038,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.2709940259999257,
+                    "total": 1.483924055999978,
                     "count": 1,
-                    "self": 1.2709940259999257
+                    "self": 1.483924055999978
                 },
                 "TrainerController.advance": {
-                    "total": 185.17632726798843,
-                    "count": 18192,
-                    "self": 0.21790039998245447,
+                    "total": 2031.0903070571067,
+                    "count": 181864,
+                    "self": 1.9976428490458602,
                     "children": {
                         "env_step": {
-                            "total": 142.81059462600797,
-                            "count": 18192,
-                            "self": 108.78446163200192,
+                            "total": 1407.2546968289648,
+                            "count": 181864,
+                            "self": 1074.0869557420808,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 33.88783405701088,
-                                    "count": 18192,
-                                    "self": 0.6471468669826663,
+                                    "total": 331.8149656088565,
+                                    "count": 181864,
+                                    "self": 6.398366203912019,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 33.24068719002821,
-                                            "count": 18192,
-                                            "self": 33.24068719002821
+                                            "total": 325.41659940494446,
+                                            "count": 181864,
+                                            "self": 325.41659940494446
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.13829893699517015,
-                                    "count": 18192,
+                                    "total": 1.3527754780275245,
+                                    "count": 181864,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 186.2964024690143,
-                                            "count": 18192,
+                                            "total": 2031.6684058839683,
+                                            "count": 181864,
                                             "is_parallel": true,
-                                            "self": 91.90503982399446,
+                                            "self": 1096.1810742638997,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0012169280000762228,
+                                                            "total": 0.0009950090000074852,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003886250001414737,
+                                                            "self": 0.0002717519998896023,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0008283029999347491,
+                                                                    "total": 0.0007232570001178829,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008283029999347491
+                                                                    "self": 0.0007232570001178829
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.017391022000083467,
+                                                            "total": 0.015677181000000928,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003446420003001549,
+                                                            "self": 0.00022112700025900267,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0002456879999499506,
+                                                                    "total": 0.00016523799990864063,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002456879999499506
+                                                                    "self": 0.00016523799990864063
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.015950279999970007,
+                                                                    "total": 0.01464410699986729,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.015950279999970007
+                                                                    "self": 0.01464410699986729
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0008504119998633541,
+                                                                    "total": 0.0006467089999659947,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00018180899996877997,
+                                                                    "self": 0.0001443310000013298,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0006686029998945742,
+                                                                            "total": 0.0005023779999646649,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0006686029998945742
+                                                                            "self": 0.0005023779999646649
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 94.39136264501985,
-                                                    "count": 18191,
+                                                    "total": 935.4873316200685,
+                                                    "count": 181863,
                                                     "is_parallel": true,
-                                                    "self": 3.6992152049976994,
+                                                    "self": 35.60573260907904,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 2.0660426019983333,
-                                                            "count": 18191,
+                                                            "total": 20.04231953900762,
+                                                            "count": 181863,
                                                             "is_parallel": true,
-                                                            "self": 2.0660426019983333
+                                                            "self": 20.04231953900762
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 77.33828555702075,
-                                                            "count": 18191,
+                                                            "total": 769.2791198750026,
+                                                            "count": 181863,
                                                             "is_parallel": true,
-                                                            "self": 77.33828555702075
+                                                            "self": 769.2791198750026
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 11.287819281003067,
-                                                            "count": 18191,
+                                                            "total": 110.56015959697925,
+                                                            "count": 181863,
                                                             "is_parallel": true,
-                                                            "self": 2.2710576070865045,
+                                                            "self": 22.2171321491287,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 9.016761673916562,
-                                                                    "count": 181910,
+                                                                    "total": 88.34302744785055,
+                                                                    "count": 1818630,
                                                                     "is_parallel": true,
-                                                                    "self": 9.016761673916562
+                                                                    "self": 88.34302744785055
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 42.147832241998,
-                            "count": 18192,
-                            "self": 0.26467858001501554,
+                            "total": 621.837967379096,
+                            "count": 181864,
+                            "self": 2.5286666780179985,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 13.53277166398334,
-                                    "count": 18192,
-                                    "self": 13.274490549983511,
+                                    "total": 135.94426321507808,
+                                    "count": 181864,
+                                    "self": 133.73425045007662,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.25828111399982845,
-                                            "count": 4,
-                                            "self": 0.25828111399982845
+                                            "total": 2.2100127650014656,
+                                            "count": 40,
+                                            "self": 2.2100127650014656
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 28.350381997999648,
-                                    "count": 19,
-                                    "self": 22.547381198998664,
+                                    "total": 483.3650374859999,
+                                    "count": 191,
+                                    "self": 388.68595532199015,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 5.8030007990009835,
-                                            "count": 570,
-                                            "self": 5.8030007990009835
+                                            "total": 94.67908216400974,
+                                            "count": 9550,
+                                            "self": 94.67908216400974
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.2429998150764732e-06,
+                    "total": 6.63000264466973e-07,
                     "count": 1,
-                    "self": 1.2429998150764732e-06
+                    "self": 6.63000264466973e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.07427533999998559,
+                    "total": 0.043453525000131776,
                     "count": 1,
-                    "self": 0.00045179900007497054,
+                    "self": 0.00045814800023435964,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.07382354099991062,
+                            "total": 0.04299537699989742,
                             "count": 1,
-                            "self": 0.07382354099991062
+                            "self": 0.04299537699989742
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,103 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 6.181818181818182,
-                "creation_time": 1756743693.4427552,
+                "steps": 1599976,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1599976.onnx",
+                "reward": 26.818181818181817,
+                "creation_time": 1756745826.9205108,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1599976.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 8.878787878787879,
-                "creation_time": 1756743740.8214815,
+                "steps": 1649992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1649992.onnx",
+                "reward": 27.703703703703702,
+                "creation_time": 1756745873.9021735,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1649992.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 12.636363636363637,
-                "creation_time": 1756743786.9100819,
+                "steps": 1699936,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1699936.onnx",
+                "reward": 28.12121212121212,
+                "creation_time": 1756745923.30265,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1699936.pt"
                 ]
             },
             {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": null,
-                "creation_time": 1756743832.776409,
+                "steps": 1749960,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1749960.onnx",
+                "reward": 28.318181818181817,
+                "creation_time": 1756745972.599262,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1749960.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": null,
-                "creation_time": 1756743832.8569334,
+                "steps": 1799984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1799984.onnx",
+                "reward": 26.818181818181817,
+                "creation_time": 1756746022.0835266,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1799984.pt"
+                ]
+            },
+            {
+                "steps": 1849984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1849984.onnx",
+                "reward": 28.0,
+                "creation_time": 1756746068.6017828,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1849984.pt"
+                ]
+            },
+            {
+                "steps": 1899944,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1899944.onnx",
+                "reward": 27.886363636363637,
+                "creation_time": 1756746118.0606852,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1899944.pt"
+                ]
+            },
+            {
+                "steps": 1949968,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1949968.onnx",
+                "reward": 27.757575757575758,
+                "creation_time": 1756746167.9905531,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1949968.pt"
+                ]
+            },
+            {
+                "steps": 1999992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1999992.onnx",
+                "reward": 27.59090909090909,
+                "creation_time": 1756746217.2514899,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1999992.pt"
+                ]
+            },
+            {
+                "steps": 2000504,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-2000504.onnx",
+                "reward": 27.59090909090909,
+                "creation_time": 1756746217.3245153,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-2000504.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1756743832.8569334,
+            "steps": 2000504,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 27.59090909090909,
+            "creation_time": 1756746217.3245153,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-2000504.pt"
             ]
         }
     },