Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+git.diff filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

.summary/0/events.out.tfevents.1696733778.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7386691d8225a5cb10ac85fccd172ac664b1284799edf192fec8855abb6b9e81
+size 7497353

.summary/1/events.out.tfevents.1696733778.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6129f6bac1ba2e3d58b4f7702cb9c7994644bd3a42733fe9398e2331f8d9e225
+size 4346782

README.md

@@ -0,0 +1,169 @@
+---
+library_name: sample-factory
+tags:
+- deep-reinforcement-learning
+- reinforcement-learning
+- sample-factory
+model-index:
+- name: APPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: atari_assault
+      type: atari_assault
+    metrics:
+    - type: mean_reward
+      value: 9944.00 +/- 1906.60
+      name: mean_reward
+      verified: false
+---
+
+A(n) **APPO** model trained on the **atari_assault** environment.
+
+This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
+Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
+
+
+## Downloading the model
+
+After installing Sample-Factory, download the model with:
+```
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_assault
+```
+
+    
+## About the Model
+
+This model as with all the others in the benchmarks was trained initially asynchronously un-seeded to 10 million steps for the purposes of setting a sample factory async baseline for this model on this environment but only 3/57 made it. 
+
+The aim is to reach state-of-the-art (SOTA) performance on each atari environment. I will flag the models with SOTA when they reach at or near these levels. 
+
+The hyperparameters used in the model are the ones I have pushed to my fork of sample-factory: https://github.com/MattStammers/sample-factory. Given that https://huggingface.co/edbeeching has kindly shared his.
+I saved time and energy by using many of his tuned hyperparameters to maximise performance. However, he used 2 billion training steps. I have started as explained above at 10 million then moved to 100m to see how performance goes:
+```
+hyperparameters =  {
+  "device": "gpu",
+  "seed": 1234,
+  "num_policies": 2,
+  "async_rl": true,
+  "serial_mode": false,
+  "batched_sampling": true,
+  "num_batches_to_accumulate": 2,
+  "worker_num_splits": 1,
+  "policy_workers_per_policy": 1,
+  "max_policy_lag": 1000,
+  "num_workers": 16,
+  "num_envs_per_worker": 2,
+  "batch_size": 1024,
+  "num_batches_per_epoch": 8,
+  "num_epochs": 4,
+  "rollout": 128,
+  "recurrence": 1,
+  "shuffle_minibatches": false,
+  "gamma": 0.99,
+  "reward_scale": 1.0,
+  "reward_clip": 1000.0,
+  "value_bootstrap": false,
+  "normalize_returns": true,
+  "exploration_loss_coeff": 0.0004677351413,
+  "value_loss_coeff": 0.5,
+  "kl_loss_coeff": 0.0,
+  "exploration_loss": "entropy",
+  "gae_lambda": 0.95,
+  "ppo_clip_ratio": 0.1,
+  "ppo_clip_value": 1.0,
+  "with_vtrace": false,
+  "vtrace_rho": 1.0,
+  "vtrace_c": 1.0,
+  "optimizer": "adam",
+  "adam_eps": 1e-05,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "max_grad_norm": 0.0,
+  "learning_rate": 0.0003033891184,
+  "lr_schedule": "linear_decay",
+  "lr_schedule_kl_threshold": 0.008,
+  "lr_adaptive_min": 1e-06,
+  "lr_adaptive_max": 0.01,
+  "obs_subtract_mean": 0.0,
+  "obs_scale": 255.0,
+  "normalize_input": true,
+  "normalize_input_keys": [
+    "obs"
+  ],
+  "decorrelate_experience_max_seconds": 0,
+  "decorrelate_envs_on_one_worker": true,
+  "actor_worker_gpus": [],
+  "set_workers_cpu_affinity": true,
+  "force_envs_single_thread": false,
+  "default_niceness": 0,
+  "log_to_file": true,
+  "experiment_summaries_interval": 3,
+  "flush_summaries_interval": 30,
+  "stats_avg": 100,
+  "summaries_use_frameskip": true,
+  "heartbeat_interval": 10,
+  "heartbeat_reporting_interval": 60,
+  "train_for_env_steps": 100000000,
+  "train_for_seconds": 10000000000,
+  "save_every_sec": 120,
+  "keep_checkpoints": 2,
+  "load_checkpoint_kind": "latest",
+  "save_milestones_sec": 1200,
+  "save_best_every_sec": 5,
+  "save_best_metric": "reward",
+  "save_best_after": 100000,
+  "benchmark": false,
+  "encoder_mlp_layers": [
+    512,
+    512
+  ],
+  "encoder_conv_architecture": "convnet_atari",
+  "encoder_conv_mlp_layers": [
+    512
+  ],
+  "use_rnn": false,
+  "rnn_size": 512,
+  "rnn_type": "gru",
+  "rnn_num_layers": 1,
+  "decoder_mlp_layers": [],
+  "nonlinearity": "relu",
+  "policy_initialization": "orthogonal",
+  "policy_init_gain": 1.0,
+  "actor_critic_share_weights": true,
+  "adaptive_stddev": false,
+  "continuous_tanh_scale": 0.0,
+  "initial_stddev": 1.0,
+  "use_env_info_cache": false,
+  "env_gpu_actions": false,
+  "env_gpu_observations": true,
+  "env_frameskip": 4,
+  "env_framestack": 4,
+  }
+
+  ```
+
+
+    
+## Using the model
+
+To run the model after download, use the `enjoy` script corresponding to this environment:
+```
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_assault --train_dir=./train_dir --experiment=APPO-atari_assault
+```
+
+
+You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
+See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
+    
+## Training with this model
+
+To continue training with this model, use the `train` script corresponding to this environment:
+```
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_assault --train_dir=./train_dir --experiment=APPO-atari_assault --restart_behavior=resume --train_for_env_steps=10000000000
+```
+
+Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
+    

checkpoint_p0/best_000097600_99942400_reward_97.070.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da399ebab95ae343498c27a1c4cf69a50b73945bebdce84f5622fe0c0b60a64e
+size 20727987

checkpoint_p0/checkpoint_000096832_99155968.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f88dc2b4c95e98961c87ef50752c45aa997b0b6c9cf4bff2ca0dc2dad41a515
+size 20728323

checkpoint_p0/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0114f289c7222f6e8bf046b70966a0fb6e5c8962101924022a84a31046f320b
+size 20728323

checkpoint_p0/milestones/checkpoint_000008384_8585216.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353138791e84864b6d47252935b03afc2ddf8229fde0e04e16fb1192f55d56fb
+size 20729179

checkpoint_p0/milestones/checkpoint_000016960_17367040.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934fbf1b5a09f3e97a37df0d2081354c69bdcc266a32375306d07fa1ecd288f5
+size 20729235

checkpoint_p0/milestones/checkpoint_000025568_26181632.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08676c37f40b7f15df77856bdc511c848e6933b1778dbb0f19cb58f69f0e916
+size 20729235

checkpoint_p0/milestones/checkpoint_000034144_34963456.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6af23710a75ee8474234e8a06e0d87eacc30dd454608159a098f53bc40aacdf
+size 20729235

checkpoint_p0/milestones/checkpoint_000042720_43745280.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cedf046f0eb6b6bce03a6c4128422624355b94395c722c67468e8f1a39f26d6f
+size 20729235

checkpoint_p0/milestones/checkpoint_000051296_52527104.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c14683e7b027c82ee8559b4a133dcb3e9da46b407d79aa00b4f5d83d677e552e
+size 20729235

checkpoint_p0/milestones/checkpoint_000059872_61308928.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9aaa21f644102570b82ac75e3c6bac54431973db124466c5ed01c8f3335726
+size 20729235

checkpoint_p0/milestones/checkpoint_000068448_70090752.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba5df5153128958f03a529434381de3848983b9a6b25f3cb9fe63e3f7a38495
+size 20729235

checkpoint_p0/milestones/checkpoint_000077056_78905344.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10aad02f6f5ef09c24cb834d66c0189f0f3f4eba3b28bede5d92bedf182b48a1
+size 20729235

checkpoint_p0/milestones/checkpoint_000085664_87719936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb8724513d534644f34b90af8726c48e9f03ba1fe0a454bd51d633732d50154
+size 20729235

checkpoint_p0/milestones/checkpoint_000094240_96501760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cbdc62539a0a4341e80dc04110d446847fddf45ec01ac15ccc2dc6b3accab5e
+size 20729235

checkpoint_p1/best_000089568_91717632_reward_98.400.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d37315cb5abd368a2d353f99dd84622f55be28ec8c15b8cf35cf4b8b6c8e388
+size 20727987

checkpoint_p1/checkpoint_000097344_99680256.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b93add38c49f3d48758029cd5b4fb13cd1a3347991a889af8a7606c79f76f5
+size 20728323

checkpoint_p1/checkpoint_000098208_100564992.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b479caeb29dd64e174970461ff3e7f4435cdc72a709ee00d82c28810986db66
+size 20728323

checkpoint_p1/milestones/checkpoint_000008448_8650752.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3998a0982b7b323142df5137a35565a895cbb03fe83e65a7003f2a7e7312b2b2
+size 20729179

checkpoint_p1/milestones/checkpoint_000017056_17465344.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c220933c90710a5d7ab09f40e38604866dc2b8ecfa575da94c443cd7200de5c8
+size 20729235

checkpoint_p1/milestones/checkpoint_000025664_26279936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb24f67919291e32f7035aa00feb98a037db1efd4827f6e123f898a45bac214d
+size 20729235

checkpoint_p1/milestones/checkpoint_000034304_35127296.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21f2a14a9f3329a5939b5a704171d2c04a22d63aa560329aa5e42ad25a4f1da7
+size 20729235

checkpoint_p1/milestones/checkpoint_000042944_43974656.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b6cea9f3e624fd0d02f71bcc521b3c26e6263b90d4a5e789824ae64b10fbe4d
+size 20729235

checkpoint_p1/milestones/checkpoint_000051584_52822016.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25a9393dd52d647b5b3b79f44157e5f2f3bc85afe6e60aace282893e2c8daa3
+size 20729235

checkpoint_p1/milestones/checkpoint_000060192_61636608.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f38c9ca53420bccc3c8045254d1bc32a7cedfea7eeb913d2820acf58ad7080be
+size 20729235

checkpoint_p1/milestones/checkpoint_000068832_70483968.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5094147bb49b3383f17bcfa8b85aa05d02775bcf576cc514a60277c697c01887
+size 20729235

checkpoint_p1/milestones/checkpoint_000077472_79331328.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:383a685f119fa801bea3dff249ef0d6d79836840a044eae7bd36f5318b0838d7
+size 20729235

checkpoint_p1/milestones/checkpoint_000086144_88211456.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb3bd4b13637cde687ba0e52da931dc8fd71992d10e617718c3d87fc6f82c89
+size 20729235

checkpoint_p1/milestones/checkpoint_000094752_97026048.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e1ab00def381a7651923783c14d4e423b92c176c53c58e01acf72bc6158710e
+size 20729235

config.json

@@ -0,0 +1,162 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "atari_assault",
+  "experiment": "atari_assault_APPO",
+  "train_dir": "./train_atari",
+  "restart_behavior": "restart",
+  "device": "gpu",
+  "seed": 1234,
+  "num_policies": 2,
+  "async_rl": true,
+  "serial_mode": false,
+  "batched_sampling": true,
+  "num_batches_to_accumulate": 2,
+  "worker_num_splits": 1,
+  "policy_workers_per_policy": 1,
+  "max_policy_lag": 1000,
+  "num_workers": 16,
+  "num_envs_per_worker": 2,
+  "batch_size": 1024,
+  "num_batches_per_epoch": 8,
+  "num_epochs": 4,
+  "rollout": 128,
+  "recurrence": 1,
+  "shuffle_minibatches": false,
+  "gamma": 0.99,
+  "reward_scale": 1.0,
+  "reward_clip": 1000.0,
+  "value_bootstrap": false,
+  "normalize_returns": true,
+  "exploration_loss_coeff": 0.0004677351413,
+  "value_loss_coeff": 0.5,
+  "kl_loss_coeff": 0.0,
+  "exploration_loss": "entropy",
+  "gae_lambda": 0.95,
+  "ppo_clip_ratio": 0.1,
+  "ppo_clip_value": 1.0,
+  "with_vtrace": false,
+  "vtrace_rho": 1.0,
+  "vtrace_c": 1.0,
+  "optimizer": "adam",
+  "adam_eps": 1e-05,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "max_grad_norm": 0.0,
+  "learning_rate": 0.0003033891184,
+  "lr_schedule": "linear_decay",
+  "lr_schedule_kl_threshold": 0.008,
+  "lr_adaptive_min": 1e-06,
+  "lr_adaptive_max": 0.01,
+  "obs_subtract_mean": 0.0,
+  "obs_scale": 255.0,
+  "normalize_input": true,
+  "normalize_input_keys": [
+    "obs"
+  ],
+  "decorrelate_experience_max_seconds": 0,
+  "decorrelate_envs_on_one_worker": true,
+  "actor_worker_gpus": [],
+  "set_workers_cpu_affinity": true,
+  "force_envs_single_thread": false,
+  "default_niceness": 0,
+  "log_to_file": true,
+  "experiment_summaries_interval": 3,
+  "flush_summaries_interval": 30,
+  "stats_avg": 100,
+  "summaries_use_frameskip": true,
+  "heartbeat_interval": 10,
+  "heartbeat_reporting_interval": 60,
+  "train_for_env_steps": 100000000,
+  "train_for_seconds": 10000000000,
+  "save_every_sec": 120,
+  "keep_checkpoints": 2,
+  "load_checkpoint_kind": "latest",
+  "save_milestones_sec": 1200,
+  "save_best_every_sec": 5,
+  "save_best_metric": "reward",
+  "save_best_after": 100000,
+  "benchmark": false,
+  "encoder_mlp_layers": [
+    512,
+    512
+  ],
+  "encoder_conv_architecture": "convnet_atari",
+  "encoder_conv_mlp_layers": [
+    512
+  ],
+  "use_rnn": false,
+  "rnn_size": 512,
+  "rnn_type": "gru",
+  "rnn_num_layers": 1,
+  "decoder_mlp_layers": [],
+  "nonlinearity": "relu",
+  "policy_initialization": "orthogonal",
+  "policy_init_gain": 1.0,
+  "actor_critic_share_weights": true,
+  "adaptive_stddev": false,
+  "continuous_tanh_scale": 0.0,
+  "initial_stddev": 1.0,
+  "use_env_info_cache": false,
+  "env_gpu_actions": false,
+  "env_gpu_observations": true,
+  "env_frameskip": 4,
+  "env_framestack": 4,
+  "pixel_format": "CHW",
+  "use_record_episode_statistics": true,
+  "with_wandb": true,
+  "wandb_user": "matt-stammers",
+  "wandb_project": "atari_APPO",
+  "wandb_group": "atari_assault",
+  "wandb_job_type": "SF",
+  "wandb_tags": [
+    "atari"
+  ],
+  "with_pbt": false,
+  "pbt_mix_policies_in_one_env": true,
+  "pbt_period_env_steps": 5000000,
+  "pbt_start_mutation": 20000000,
+  "pbt_replace_fraction": 0.3,
+  "pbt_mutation_rate": 0.15,
+  "pbt_replace_reward_gap": 0.1,
+  "pbt_replace_reward_gap_absolute": 1e-06,
+  "pbt_optimize_gamma": false,
+  "pbt_target_objective": "true_objective",
+  "pbt_perturb_min": 1.1,
+  "pbt_perturb_max": 1.5,
+  "command_line": "--algo=APPO --env=atari_assault --experiment=atari_assault_APPO --num_policies=2 --restart_behavior=restart --train_dir=./train_atari --train_for_env_steps=100000000 --seed=1234 --num_workers=16 --num_envs_per_worker=2 --num_batches_per_epoch=8 --async_rl=true --batched_sampling=true --batch_size=1024 --max_grad_norm=0 --learning_rate=0.0003033891184 --heartbeat_interval=10 --heartbeat_reporting_interval=60 --save_milestones_sec=1200 --num_epochs=4 --exploration_loss_coeff=0.0004677351413 --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari_APPO --wandb_group=atari_assault --wandb_job_type=SF --wandb_tags=atari",
+  "cli_args": {
+    "algo": "APPO",
+    "env": "atari_assault",
+    "experiment": "atari_assault_APPO",
+    "train_dir": "./train_atari",
+    "restart_behavior": "restart",
+    "seed": 1234,
+    "num_policies": 2,
+    "async_rl": true,
+    "batched_sampling": true,
+    "num_workers": 16,
+    "num_envs_per_worker": 2,
+    "batch_size": 1024,
+    "num_batches_per_epoch": 8,
+    "num_epochs": 4,
+    "exploration_loss_coeff": 0.0004677351413,
+    "max_grad_norm": 0.0,
+    "learning_rate": 0.0003033891184,
+    "heartbeat_interval": 10,
+    "heartbeat_reporting_interval": 60,
+    "train_for_env_steps": 100000000,
+    "save_milestones_sec": 1200,
+    "with_wandb": true,
+    "wandb_user": "matt-stammers",
+    "wandb_project": "atari_APPO",
+    "wandb_group": "atari_assault",
+    "wandb_job_type": "SF",
+    "wandb_tags": [
+      "atari"
+    ]
+  },
+  "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
+  "git_repo_name": "not a git repository",
+  "wandb_unique_id": "atari_assault_APPO_20231008_035616_217697"
+}

git.diff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3357904f421d3f4924836316b1741bf64d5dd0e807d5e80ac07059b4c52a7008
+size 14426734

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b918de85ca8dacf2084851089810ad5faeb3e254e7fdeb5dd76f1a1c901ef9
+size 13997240