Third Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e843396e8281fac34de995b25c21de45af9143b4e6df5221d85e8f8b31ff7e4
+oid sha256:7d5594df72e42f1c586def86c06b110459e7ab987db3cf6dae1827bf79680010
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c1ec393409ae64a4b81426e73cf4ad567cea3998ad999d85b497f3b2a5b8fc4
+oid sha256:5c1a928256d3e8ae5decae233d1340f394b96a9f1256c898722d7edd9846ef44
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67212738c613d044d2179116d3f56a1eb7729ffca02d8efc6254b8583850c482
+oid sha256:cc31fa081da4b5c9a965be64a4f579d545e52675649288fd5de5d33e35ced956
 size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e843396e8281fac34de995b25c21de45af9143b4e6df5221d85e8f8b31ff7e4
+oid sha256:7d5594df72e42f1c586def86c06b110459e7ab987db3cf6dae1827bf79680010
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a1862468ef4b348b2f4df8d741c3bb5c12eb3d7b29bbdbb651c32e519b7a66b
+oid sha256:c452d0f513949c9fa812bc0f3812ac861db604addf3ccb710ed0ac8fe304118a
 size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e843396e8281fac34de995b25c21de45af9143b4e6df5221d85e8f8b31ff7e4
+oid sha256:7d5594df72e42f1c586def86c06b110459e7ab987db3cf6dae1827bf79680010
 size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a5b94735bb4e59341903cd32cfec451caef2cb63c03963ec24bc50b4b77a2c
+oid sha256:329a3668ae9bc4eae214304867d1dd2d4c8d93c151853a24bba219cde9a2d044
 size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0d0c386089f77fe9d269c47d0defb041eb4a800de4f12665f24d7a9a3ac3c7e
+oid sha256:56a73f63927826a5d7b62ada23b26b1a66740e4f659e33f95d7de64dad6eeeec
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:795eabf52be17d500d53d1b2784b92e3577a12e6a2cc318094c1671f28f64a12
+oid sha256:ebaf647be94307ab05bf349f8d936643d2e68741b890691de0aa0e6ac0b06232
 size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec2c451f916830b24e5348552cfa02c914b6db05a2803c8d868484daacde1fe5
+oid sha256:ce9c1f9d10a952a00352d66b7506920e9876e77218ee4bdac2589c0b2bd2efed
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cd8a3857e0224046108fdc9f5c604bed3c821cbeb83c7dba99600e27fa6f3f9
+oid sha256:e2e4a12d276ac0bd25e3b62d7b23558de8da37f1e3c065516c808be05a7de3e2
 size 3850000

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21321d42bc6077958c3d5a89a5b67e9af2ea1c6b139a6f7ee0ee7d7e1877fa00
+oid sha256:7cc217183430f560c7ac436a46b06b63af1ec97e0bb0eb3ce859624c951842e1
 size 3849250

SnowballTarget/events.out.tfevents.1739107944.f8f55f8fb9b1.10066.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59bb48a3be06fbe0e7a4b784c668d54b4744d333011d54cfa9757aa742fcf39c
+size 23527

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "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": true, "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": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -69,8 +69,8 @@ checkpoint_settings:
   run_id: SnowballTarget1
   initialize_from: null
   load_model: false
-  resume: true
-  force: false
+  resume: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.086 seconds
+- Completed reload, in  0.097 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)
@@ -42,7 +42,7 @@ 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: 0.704866 ms
+UnloadTime: 0.678538 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 1 worker threads for Enlighten.
@@ -50,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      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
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -78,7 +78,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 2.8 KB
+      Peak Allocated Bytes 3.6 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -166,19 +166,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 36
     [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]: 1 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.6 MB
+      Peak Allocated memory 6.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.7 MB
@@ -195,7 +195,7 @@ Memory Statistics:
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
   Initial Block Size 2.0 MB
-  Used Block Count 1
+  Used Block Count 2
   Overflow Count (too large) 0
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -210,13 +210,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5081 frames, [64.0 KB-128.0 KB]: 377 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 KB
+      Peak Allocated memory 66.7 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -228,13 +228,13 @@ 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]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5458 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.5 MB
+      Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5457 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
@@ -246,13 +246,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1 frames
+      Peak usage frame count: [0-1.0 KB]: 5458 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]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -1,50 +1,358 @@
 {
     "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.8317452073097229,
+            "min": 0.8317452073097229,
+            "max": 2.86214280128479,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7904.90625,
+            "min": 7904.90625,
+            "max": 29216.75390625,
+            "count": 20
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.87293815612793,
+            "min": 0.3050481975078583,
+            "max": 12.87293815612793,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2510.222900390625,
+            "min": 59.17934799194336,
+            "max": 2601.0673828125,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07268064973890004,
+            "min": 0.06214246416807417,
+            "max": 0.07867881900011864,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.29072259895560015,
+            "min": 0.24856985667229667,
+            "max": 0.3725369908677428,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.1921825854874709,
+            "min": 0.12688603054038158,
+            "max": 0.30848638310151943,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7687303419498837,
+            "min": 0.5075441221615263,
+            "max": 1.5424319155075972,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.082097306000005e-06,
+            "min": 8.082097306000005e-06,
+            "max": 0.000291882002706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.232838922400002e-05,
+            "min": 3.232838922400002e-05,
+            "max": 0.00138516003828,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10269400000000001,
+            "min": 0.10269400000000001,
+            "max": 0.19729400000000002,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.41077600000000003,
+            "min": 0.41077600000000003,
+            "max": 0.96172,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0001444306000000001,
+            "min": 0.0001444306000000001,
+            "max": 0.0048649706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005777224000000004,
+            "min": 0.0005777224000000004,
+            "max": 0.023089828,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.75,
+            "min": 3.590909090909091,
+            "max": 25.75,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1133.0,
+            "min": 158.0,
+            "max": 1385.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.75,
+            "min": 3.590909090909091,
+            "max": 25.75,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1133.0,
+            "min": 158.0,
+            "max": 1385.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1739107782",
+        "start_time_seconds": "1739107943",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn --resume ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.6.0+cu124",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1739107785"
+        "end_time_seconds": "1739108370"
     },
-    "total": 3.6425648360000196,
+    "total": 427.5024893069999,
     "count": 1,
-    "self": 0.8001334569999017,
+    "self": 0.4380111699997542,
     "children": {
         "run_training.setup": {
-            "total": 0.022948951000216766,
+            "total": 0.021245147000172437,
             "count": 1,
-            "self": 0.022948951000216766
+            "self": 0.021245147000172437
         },
         "TrainerController.start_learning": {
-            "total": 2.819482427999901,
+            "total": 427.04323299,
             "count": 1,
-            "self": 0.00017423999997845385,
+            "self": 0.34450161702488913,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.503075215000081,
+                    "total": 2.233746338000401,
                     "count": 1,
-                    "self": 2.503075215000081
+                    "self": 2.233746338000401
+                },
+                "TrainerController.advance": {
+                    "total": 424.37310269597447,
+                    "count": 18192,
+                    "self": 0.36735161699198216,
+                    "children": {
+                        "env_step": {
+                            "total": 298.66908398901614,
+                            "count": 18192,
+                            "self": 227.55397627603315,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 70.90680342899259,
+                                    "count": 18192,
+                                    "self": 1.2187335560574866,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 69.6880698729351,
+                                            "count": 18192,
+                                            "self": 69.6880698729351
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.20830428399040102,
+                                    "count": 18192,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 425.45446078197665,
+                                            "count": 18192,
+                                            "is_parallel": true,
+                                            "self": 225.87444271795857,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0021840249996785133,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006801879990234738,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0015038370006550394,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0015038370006550394
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.06548560800001724,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005569240001932485,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003473779997875681,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003473779997875681
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.06272946099988985,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.06272946099988985
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001851845000146568,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003541890005180903,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0014976559996284777,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0014976559996284777
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 199.58001806401808,
+                                                    "count": 18191,
+                                                    "is_parallel": true,
+                                                    "self": 9.514904223998656,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.287402872990242,
+                                                            "count": 18191,
+                                                            "is_parallel": true,
+                                                            "self": 5.287402872990242
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 154.53151239704312,
+                                                            "count": 18191,
+                                                            "is_parallel": true,
+                                                            "self": 154.53151239704312
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 30.246198569986063,
+                                                            "count": 18191,
+                                                            "is_parallel": true,
+                                                            "self": 5.332871644017814,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 24.91332692596825,
+                                                                    "count": 181910,
+                                                                    "is_parallel": true,
+                                                                    "self": 24.91332692596825
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 125.33666708996634,
+                            "count": 18192,
+                            "self": 0.40465278698684415,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 26.82514596097826,
+                                    "count": 18192,
+                                    "self": 26.23723380197862,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.587912158999643,
+                                            "count": 4,
+                                            "self": 0.587912158999643
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 98.10686834200123,
+                                    "count": 90,
+                                    "self": 39.50551661198142,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 58.601351730019815,
+                                            "count": 4587,
+                                            "self": 58.601351730019815
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
                 },
                 "trainer_threads": {
-                    "total": 1.4239999472920317e-06,
+                    "total": 8.420001904596575e-07,
                     "count": 1,
-                    "self": 1.4239999472920317e-06
+                    "self": 8.420001904596575e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.3162315489998946,
+                    "total": 0.09188149700003123,
                     "count": 1,
-                    "self": 0.0015873279999141232,
+                    "self": 0.001107937000142556,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.31464422099998046,
+                            "total": 0.09077355999988868,
                             "count": 1,
-                            "self": 0.31464422099998046
+                            "self": 0.09077355999988868
                         }
                     }
                 }

run_logs/training_status.json

@@ -4,8 +4,8 @@
             {
                 "steps": 49936,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 17.181818181818183,
-                "creation_time": 1739106886.2487252,
+                "reward": 14.454545454545455,
+                "creation_time": 1739108051.009652,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
                 ]
@@ -13,8 +13,8 @@
             {
                 "steps": 99960,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 25.363636363636363,
-                "creation_time": 1739106991.901262,
+                "reward": 20.90909090909091,
+                "creation_time": 1739108159.3707573,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
@@ -22,8 +22,8 @@
             {
                 "steps": 149984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 25.727272727272727,
-                "creation_time": 1739107096.7528453,
+                "reward": 24.636363636363637,
+                "creation_time": 1739108265.4082656,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
@@ -31,8 +31,8 @@
             {
                 "steps": 199984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.545454545454547,
-                "creation_time": 1739107203.4904578,
+                "reward": 25.636363636363637,
+                "creation_time": 1739108370.398381,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
@@ -40,17 +40,8 @@
             {
                 "steps": 200112,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.545454545454547,
-                "creation_time": 1739107203.5898087,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
-                ]
-            },
-            {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": null,
-                "creation_time": 1739107785.1119068,
+                "reward": 25.636363636363637,
+                "creation_time": 1739108370.502435,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
@@ -59,8 +50,8 @@
         "final_checkpoint": {
             "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1739107785.1119068,
+            "reward": 25.636363636363637,
+            "creation_time": 1739108370.502435,
             "auxillary_file_paths": [
                 "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]