Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1696879709.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a3ebf03f17f751b507ba72f72bf5dec3597e9145a34aa00c5bd43df47a69805
+size 7948989

.summary/1/events.out.tfevents.1696879709.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b077754a836369406599e984c8ad07058eaeb3f34771ebd4a13b99014b154851
+size 4600634

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_breakout
     metrics:
     - type: mean_reward
-      value: 126.40 +/- 78.46
+      value: 495.10 +/- 169.27
       name: mean_reward
       verified: false
 ---
@@ -30,15 +30,128 @@ Documentation for how to use Sample-Factory can be found at https://www.samplefa
 
 After installing Sample-Factory, download the model with:
 ```
-python -m sample_factory.huggingface.load_from_hub -r MattStammers/appo-atari_breakout
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_breakout
 ```
 
     
+## 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_breakout --train_dir=./train_dir --experiment=appo-atari_breakout
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_breakout --train_dir=./train_dir --experiment=APPO-atari_breakout
 ```
 
 
@@ -49,7 +162,7 @@ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
 
 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_breakout --train_dir=./train_dir --experiment=appo-atari_breakout --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_breakout --train_dir=./train_dir --experiment=APPO-atari_breakout --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_000095072_97353728_reward_35.860.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d43cefcd6a33db18427f287db7f2dc4d827ad8b4bc73a934680c3d7f53fab42
+size 20709555

checkpoint_p0/checkpoint_000096928_99254272.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a88f204af596926a676d857ba079161c047f3c2c91c3124219fab1cc44ab95
+size 20709891

checkpoint_p0/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1edde2012844e9566f899a3ab8a9d9a6d9cf0977a45eebe4f7ad7d5b3f9b69e5
+size 20709891

checkpoint_p0/milestones/checkpoint_000007776_7962624.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be66bb45407970c661a0ad0a68c1c7a9d789892e121064a4c7e215e3d2abcf85
+size 20710747

checkpoint_p0/milestones/checkpoint_000015776_16154624.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6396b26e6ceb089bad59505daf18ce13da249d78b5c42ef9c9d3109c7ae764b0
+size 20710803

checkpoint_p0/milestones/checkpoint_000023840_24412160.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fccf1f07b6586d66be1803f495c73561064a4923adef49ac8b879765be4f573
+size 20710803

checkpoint_p0/milestones/checkpoint_000031904_32669696.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4cbcda7826c4b920e5f12aeebfdbfcf64e8b0dbe0025244353228a6619b5bef
+size 20710803

checkpoint_p0/milestones/checkpoint_000040032_40992768.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd9c158e33c0b30522fc34fa9be91d3990b82d8c6814bc3a25f140e6bf43617
+size 20710803

checkpoint_p0/milestones/checkpoint_000048128_49283072.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27735661d5c1e256f00e91b3d9af64f564eb829d865fad892aa13eb0d8dc0925
+size 20710803

checkpoint_p0/milestones/checkpoint_000056256_57606144.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ac8e54f775fe7ef72c57812d001dbc239a3b0c7b8655170821e3649527b460
+size 20710803

checkpoint_p0/milestones/checkpoint_000064384_65929216.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a58fc2829061ce63ca5a549f955c182839707a8e29a1029c3f6ec99b954df8b
+size 20710803

checkpoint_p0/milestones/checkpoint_000072512_74252288.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e12f3df0e860406923a2373e0497171a2507b9f5bf2aafb14fe5dc02977b45
+size 20710803

checkpoint_p0/milestones/checkpoint_000080640_82575360.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88f5853a44df96fbc0bb812ac4ce1772d6ab601b01695d88d7fd3be712859216
+size 20710803

checkpoint_p0/milestones/checkpoint_000088768_90898432.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da20132dff513b77870d01a1895c2947d545c458f47e8f7f78ab13edcd312732
+size 20710803

checkpoint_p0/milestones/checkpoint_000096928_99254272.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5c91bb0956e375032cbf162cbd111db973e4694137fef50696c672fabd7e47
+size 20710803

checkpoint_p1/best_000097984_100335616_reward_37.490.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73805f3bbbe2953607675a40f880496703ab8a8111d7c77206e3130dfd082e2c
+size 20709555

checkpoint_p1/checkpoint_000098240_100597760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2012b73fbb2ffc6eebcb34adcc83c54e449dc277106bb13a38f91e0cc9bf14c
+size 20709891

checkpoint_p1/checkpoint_000099008_101384192.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6d02cc571cd7790ee408fdcafb6ddc8e430fcc5786d8b80e9f6fc308c267e3
+size 20709891

checkpoint_p1/milestones/checkpoint_000007872_8060928.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ece14936cfe57ff8ed557e841ef13a030e493b688986b4804976873a9dac49e
+size 20710747

checkpoint_p1/milestones/checkpoint_000016000_16384000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117254111e818264b1ad60d78c76595b5ed35be01b258f3be2bc2961e0a3b9ef
+size 20710803

checkpoint_p1/milestones/checkpoint_000024160_24739840.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b028f889bc8297d70546c99f1683ff3235e1bf673a07d9f098f5260569886d
+size 20710803

checkpoint_p1/milestones/checkpoint_000032384_33161216.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:878e67beb46250f726b81b75234f38be3c8b321cce5b18557fb21987279a5bf4
+size 20710803

checkpoint_p1/milestones/checkpoint_000040608_41582592.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a65d524d5dec69fb10240908af41bd0648459761064f1b70eec936945ec662
+size 20710803

checkpoint_p1/milestones/checkpoint_000048832_50003968.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7181ab901ea9fd7ea70741f84737b1be252026ab7378f4fdec58095bdd6e00ff
+size 20710803

checkpoint_p1/milestones/checkpoint_000057088_58458112.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee7eebd85cf1d713527afb6a8c4ef85da1b03c26f78b45d49fea5ba390af9250
+size 20710803

checkpoint_p1/milestones/checkpoint_000065312_66879488.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152f57bf231d5575d4b9d73e31782d3769ae8b34b18ef07cf8d8376b631a6f58
+size 20710803

checkpoint_p1/milestones/checkpoint_000073536_75300864.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b28d12efdf67354df6f2c6a5fdd0c8b46af9e97ccb2d60c57d7e13895226ff
+size 20710803

checkpoint_p1/milestones/checkpoint_000081792_83755008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f220c95e75757ec09aa7bd814115c1926e87727e3ce5e56e9c08df8b31fc09b
+size 20710803

checkpoint_p1/milestones/checkpoint_000090016_92176384.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bf113497d2948ce36a6d42448642f0fe8be6f8bba569a4f3ffd95090ef23a54
+size 20710803

checkpoint_p1/milestones/checkpoint_000098240_100597760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5063def9f98c26ba4b7662d1f7235acfa5cac1be9a5971142edec95eecaa4f
+size 20710859

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_breakout",
-  "experiment": "atari_breakout",
+  "experiment": "atari_breakout_APPO",
   "train_dir": "./train_atari",
-  "restart_behavior": "resume",
+  "restart_behavior": "restart",
   "device": "gpu",
-  "seed": null,
+  "seed": 1234,
   "num_policies": 2,
-  "async_rl": false,
+  "async_rl": true,
   "serial_mode": false,
-  "batched_sampling": false,
+  "batched_sampling": true,
   "num_batches_to_accumulate": 2,
   "worker_num_splits": 1,
   "policy_workers_per_policy": 1,
   "max_policy_lag": 1000,
-  "num_workers": 8,
-  "num_envs_per_worker": 1,
-  "batch_size": 256,
-  "num_batches_per_epoch": 4,
+  "num_workers": 16,
+  "num_envs_per_worker": 2,
+  "batch_size": 1024,
+  "num_batches_per_epoch": 8,
   "num_epochs": 4,
   "rollout": 128,
   "recurrence": 1,
@@ -28,7 +28,7 @@
   "reward_clip": 1000.0,
   "value_bootstrap": false,
   "normalize_returns": true,
-  "exploration_loss_coeff": 0.01,
+  "exploration_loss_coeff": 0.0004677351413,
   "value_loss_coeff": 0.5,
   "kl_loss_coeff": 0.0,
   "exploration_loss": "entropy",
@@ -42,8 +42,8 @@
   "adam_eps": 1e-05,
   "adam_beta1": 0.9,
   "adam_beta2": 0.999,
-  "max_grad_norm": 0.5,
-  "learning_rate": 0.00025,
+  "max_grad_norm": 0.0,
+  "learning_rate": 0.0003033891184,
   "lr_schedule": "linear_decay",
   "lr_schedule_kl_threshold": 0.008,
   "lr_adaptive_min": 1e-06,
@@ -51,7 +51,9 @@
   "obs_subtract_mean": 0.0,
   "obs_scale": 255.0,
   "normalize_input": true,
-  "normalize_input_keys": null,
+  "normalize_input_keys": [
+    "obs"
+  ],
   "decorrelate_experience_max_seconds": 0,
   "decorrelate_envs_on_one_worker": true,
   "actor_worker_gpus": [],
@@ -63,14 +65,14 @@
   "flush_summaries_interval": 30,
   "stats_avg": 100,
   "summaries_use_frameskip": true,
-  "heartbeat_interval": 20,
-  "heartbeat_reporting_interval": 180,
-  "train_for_env_steps": 10000000,
+  "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": -1,
+  "save_milestones_sec": 1200,
   "save_best_every_sec": 5,
   "save_best_metric": "reward",
   "save_best_after": 100000,
@@ -104,7 +106,7 @@
   "use_record_episode_statistics": true,
   "with_wandb": true,
   "wandb_user": "matt-stammers",
-  "wandb_project": "atari",
+  "wandb_project": "atari_APPO",
   "wandb_group": "atari_breakout",
   "wandb_job_type": "SF",
   "wandb_tags": [
@@ -122,16 +124,32 @@
   "pbt_target_objective": "true_objective",
   "pbt_perturb_min": 1.1,
   "pbt_perturb_max": 1.5,
-  "command_line": "--algo=APPO --env=atari_breakout --experiment=atari_breakout --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_breakout --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_breakout --experiment=atari_breakout_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_breakout --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_breakout",
-    "experiment": "atari_breakout",
+    "experiment": "atari_breakout_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",
+    "wandb_project": "atari_APPO",
     "wandb_group": "atari_breakout",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_breakout_20230925_220818_414807"
+  "wandb_unique_id": "atari_breakout_APPO_20231009_202826_479299"
 }

git.diff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f3fe545f35e5db1e419bf1e198c0bc5ef89459d55f59e2d06d3c108907e732
-size 14403396
+oid sha256:3357904f421d3f4924836316b1741bf64d5dd0e807d5e80ac07059b4c52a7008
+size 14426734

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0cdf0b5ac887672d74465b25b031b3407bcb4729f5bfb2daac9a9bd78171529
-size 1134185
+oid sha256:5160ae3473d15b0ba78a11663966e5ff5f1af1c6cd182c30275e1cce9e97c017
+size 3013766