Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697076190.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe80dbddb74d52a82a650a635fea40ee447ea73d4cf13d2169b7e508a603399
+size 8602139

.summary/1/events.out.tfevents.1697076190.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db172a5dde1b720bd22e9b965788d0c1971d45fbe1e923dcf8a494137493314
+size 4964033

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_hero
     metrics:
     - type: mean_reward
-      value: 10772.50 +/- 2568.25
+      value: 35738.00 +/- 2517.72
       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_hero
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_hero
 ```
 
     
+## 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_hero --train_dir=./train_dir --experiment=appo-atari_hero
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_hero --train_dir=./train_dir --experiment=APPO-atari_hero
 ```
 
 
@@ -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_hero --train_dir=./train_dir --experiment=appo-atari_hero --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_hero --train_dir=./train_dir --experiment=APPO-atari_hero --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_000067200_68812800_reward_71.210.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b183263c980d96bebc27d924d868b6201f3a48d81f672eec82d6d19b0230e6
+size 20795763

checkpoint_p0/checkpoint_000097984_100335616.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa97a3aeb1925cf776ada0ce2e4441d57585c7b8d831e36171619de5eb361c8d
+size 20796099

checkpoint_p0/checkpoint_000098144_100499456.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d20d3b121cd4579cd27b04a7e0d82c7d23b39a5745a92aa00afe570e5e70c14c
+size 20796099

checkpoint_p0/milestones/checkpoint_000007360_7536640.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7bcb53ebc3ffaa629b8a02c262e125ec50c203b21954fcf1738f98cd9ea1fa
+size 20796955

checkpoint_p0/milestones/checkpoint_000014848_15204352.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955e0c53e2c9518a45c874a93f57371790d32cdfcaee69578fdf27660388675f
+size 20797011

checkpoint_p0/milestones/checkpoint_000022336_22872064.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33780b362ecd632aff25d8b660a64456a47e1eef69a7f2b99c9fbbbed12b1d4f
+size 20797011

checkpoint_p0/milestones/checkpoint_000029824_30539776.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bb9c4a8a2847480fd6404d186ef0a8b288d07e38da753fb0dec3111799ac4dc
+size 20797011

checkpoint_p0/milestones/checkpoint_000037312_38207488.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdee171fc0d451d11a560a6ee08df7eb250131f7b98c0df5d693455f4d306d16
+size 20797011

checkpoint_p0/milestones/checkpoint_000044800_45875200.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dffd4e48f64d64ac1700126aeaa60c17e63046319021071b3f04e2d6ba48f940
+size 20797011

checkpoint_p0/milestones/checkpoint_000052288_53542912.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533b7b38ef95fcf0a248bf25032ad369ec99b9848e31b8e5f5c4448c357259fc
+size 20797011

checkpoint_p0/milestones/checkpoint_000059776_61210624.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f1ec88ef132db77bd7da3bfe5e97d9e194daa2ccb8f245132505d464fb7726
+size 20797011

checkpoint_p0/milestones/checkpoint_000067232_68845568.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459a7716409f55050eb1d59ca3e7ce68a83a68b25b9b42186b08863cdae9c280
+size 20797011

checkpoint_p0/milestones/checkpoint_000074752_76546048.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa202403478b9be549bf64c4b2f1a64df32a73f858e520c87d34a6ad43113413
+size 20797011

checkpoint_p0/milestones/checkpoint_000082240_84213760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bef74df81111f3b1f59bf54e1048d719e047d0f4a2f342a604f7b84e891cdbf
+size 20797011

checkpoint_p0/milestones/checkpoint_000089728_91881472.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f847191875e2791bc6ed568825daaf496023c1d2e157f750852d5c834251489
+size 20797011

checkpoint_p0/milestones/checkpoint_000097248_99581952.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b78dac33d71e6421516a4d27137d8dfb0d059cf15123b097638c12718c5668b
+size 20797011

checkpoint_p1/best_000079776_81690624_reward_63.630.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117f32f1112d714700dda1e06c84021ebfdb9ffdd0493e78d9c1003466d895bb
+size 20795763

checkpoint_p1/checkpoint_000097504_99844096.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b61160b997e367961d3632c2351f2ff7f30abaddcf623966fd326a5eaff41c
+size 20796099

checkpoint_p1/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f967bec32f20806458129b2f3ff60d227275aa14184159cb0b51261ba804280
+size 20796099

checkpoint_p1/milestones/checkpoint_000007328_7503872.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c0ce25540bb3ebdca316fc4d0d680c8b57f447a957c10a679c67017a501a7d3
+size 20796955

checkpoint_p1/milestones/checkpoint_000014752_15106048.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a34b1a2469f9881cfe09d4c3c02fee23356f8a41d8df9144cde334ee6b6abb7
+size 20797011

checkpoint_p1/milestones/checkpoint_000022240_22773760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8d70d374cd1c811812efe415ead06b3fc395e68c0d86823388d836c689e8f8
+size 20797011

checkpoint_p1/milestones/checkpoint_000029696_30408704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba2f049dda2b2067934f0331513019d6be416e9b557586087e7384807ecc3e01
+size 20797011

checkpoint_p1/milestones/checkpoint_000037120_38010880.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b9803e343bed7f2f0236085d7cb13c082c715f8fe9aa81749e0d34f9370cee2
+size 20797011

checkpoint_p1/milestones/checkpoint_000044576_45645824.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76bc0ea258ad4354972bb53d066d74fa6bce33f3530c771849380e07b77438eb
+size 20797011

checkpoint_p1/milestones/checkpoint_000052032_53280768.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8acd2bd7a5ed142f27cc85c3cea4ec1d772071439615b88826db127c58c11a7b
+size 20797011

checkpoint_p1/milestones/checkpoint_000059488_60915712.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9811c1ad81c164e8b5c9e4d1c308c84e3662b993f91755c70980162206196b2b
+size 20797011

checkpoint_p1/milestones/checkpoint_000066912_68517888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66bbb1a6c76b525fc7da7b8658c5e95b5aacd7ee8f8cc7ebe097aeb6f6dbd63b
+size 20797011

checkpoint_p1/milestones/checkpoint_000074400_76185600.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108946bc77774d019fe5dcb2bca943919d5cc4374ebebdba4ae24aea5baadb09
+size 20797011

checkpoint_p1/milestones/checkpoint_000081856_83820544.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18885a95b5e85cc209a99c4bc779908104cbf06e9a702c40d6c86c63784915f1
+size 20797011

checkpoint_p1/milestones/checkpoint_000089312_91455488.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a471fa1879bcc1d3beddaff4874acbfc7a6f4948d881e218c28f7b9790ece0
+size 20797011

checkpoint_p1/milestones/checkpoint_000096768_99090432.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d724a4482018479be5c5b70c176bc832f5cb3d597734b6b493d4965dea385ae4
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_hero",
-  "experiment": "atari_hero",
+  "experiment": "atari_hero_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_hero",
   "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_hero --experiment=atari_hero --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_hero --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_hero --experiment=atari_hero_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_hero --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_hero",
-    "experiment": "atari_hero",
+    "experiment": "atari_hero_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_hero",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_hero_20230926_103007_211865"
+  "wandb_unique_id": "atari_hero_APPO_20231012_030307_335840"
 }

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:b4b307f32618c37f9b1062cc2cc0fe756e1c221ad55c20ab61adb55efb75c1c7
-size 1808199
+oid sha256:c312d0e49540460529c9859af71cb7eead600c5ca46be56ba97dda0a101ed909
+size 4224392