Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697255978.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99fa98d7887585dedeb0f474fe9ebbfa08d09cd8236164051b3d8fab15de3ed9
+size 8239570

.summary/1/events.out.tfevents.1697255978.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19d0fbc5c561dee80e041de3e0e9e1e5e648776b5994d571ed7ed56808bae758
+size 4752719

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_privateye
     metrics:
     - type: mean_reward
-      value: 80.00 +/- 40.00
+      value: 100.00 +/- 0.00
       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_privateye
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_privateye
 ```
 
     
+## 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_privateye --train_dir=./train_dir --experiment=appo-atari_privateye
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_privateye --train_dir=./train_dir --experiment=APPO-atari_privateye
 ```
 
 
@@ -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_privateye --train_dir=./train_dir --experiment=appo-atari_privateye --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_privateye --train_dir=./train_dir --experiment=APPO-atari_privateye --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_000044192_45252608_reward_1.010.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb150dad9ec100b7d88174b7e0751e6591d5a239ba3c033de7187783c81ea18
+size 20795763

checkpoint_p0/checkpoint_000097632_99975168.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d62d69c28fd2abb5ee15d34e120cb734659e536cf14c42f34ac6a782ee3549
+size 20796099

checkpoint_p0/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b441b2dba64e6097771e855a65feb35e99602752870f8ea57eb1bfd2c2cca779
+size 20796099

checkpoint_p0/milestones/checkpoint_000007648_7831552.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93fd24a49752c323bdd862828022af327ac8a687a007fc67d06f0c1145ff5510
+size 20796955

checkpoint_p0/milestones/checkpoint_000015424_15794176.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1210261b2aaeebfbe299497c4c413520bd85fccad1d45b1283d8770670580e94
+size 20797011

checkpoint_p0/milestones/checkpoint_000023200_23756800.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6bfeca8735c40f0da378d55f353aac8d3a93ec056bf4f555a65052a44ac3533
+size 20797011

checkpoint_p0/milestones/checkpoint_000030976_31719424.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bac493f76c9fc997dd3ffe2cc7e6df5fc5d7085d5c3e31c7107ff3096238dd9
+size 20797011

checkpoint_p0/milestones/checkpoint_000038720_39649280.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a75fc14bf0ce660846154e6880ccfbedff3fe24e5e15e5e19b232570bfd629
+size 20797011

checkpoint_p0/milestones/checkpoint_000046464_47579136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974bcde4b73755777af64e705c0debe38d612f8b2f69768fb39d70b7aab983dc
+size 20797011

checkpoint_p0/milestones/checkpoint_000054208_55508992.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:505310cc0a401803685e5219ac42479b0ad1dfacebcd1aa4979a7ab3f0154f76
+size 20797011

checkpoint_p0/milestones/checkpoint_000061920_63406080.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5167222d77f1c4274e20a02dfc86661a7c14cecbcba73aabf1b61fb5e47af612
+size 20797011

checkpoint_p0/milestones/checkpoint_000069664_71335936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791448f38da663b99982ebc4e41fdd575de2c20ad02428cbbfdea50dd2d59112
+size 20797011

checkpoint_p0/milestones/checkpoint_000077440_79298560.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c172f89e48f51f80a1144c9fa1b791c6ffee6de70b6c634c8c49e428ad09b9a5
+size 20797011

checkpoint_p0/milestones/checkpoint_000085216_87261184.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f3d3eb6d7d6195cefd016c18455702dc3d874ec4f78eb9fcb8bff818155cf2
+size 20797011

checkpoint_p0/milestones/checkpoint_000092960_95191040.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11966f5bd20f4933620eb8f3c72ec02a5a3c1dff146aa1edfd3e7ccdc8e4fa28
+size 20797011

checkpoint_p1/best_000000160_163840_reward_1.000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b10f5b1482da905c496b41ca6a81940a84c4de379627299bfefcda8dde7cd8a
+size 20795763

checkpoint_p1/checkpoint_000097792_100139008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f614f8ee96199d47e061f1cda045c832736dc5eccfbb22fb1081d95f6140111
+size 20796099

checkpoint_p1/checkpoint_000097824_100171776.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb48d0ab676c8cae6e6bfdef1a29c6598bf425a8e4e0cfff4a21add2eda0a02
+size 20796099

checkpoint_p1/milestones/checkpoint_000007616_7798784.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e860494913d52d213100777a4febb220b642c432be0a9727e9b762590c84196b
+size 20796955

checkpoint_p1/milestones/checkpoint_000015392_15761408.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f401586b4bfb35f089ac680770d6a1748c574b72cbfd9898e9d0886d79c665
+size 20797011

checkpoint_p1/milestones/checkpoint_000023168_23724032.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b08d88d56c1097b88ccc4144bf95011b518fb648e9b94effd16b15b4ef43c7e
+size 20797011

checkpoint_p1/milestones/checkpoint_000030944_31686656.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da644eda8461e30b0f9f95a817470e384ba17caaa0659a431d2a055428f0d9dd
+size 20797011

checkpoint_p1/milestones/checkpoint_000038720_39649280.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b99e112f0e98b686e739dd091fd000c008a8ace6520197750beee3f95252b8
+size 20797011

checkpoint_p1/milestones/checkpoint_000046496_47611904.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e508ed4f2778f4d1c38e353ed10e206c4284d6b72de7498167d98cc69580035
+size 20797011

checkpoint_p1/milestones/checkpoint_000054272_55574528.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62cd60851520d6cad285551da00b19534c0d676a54262b41338cc6e9e22cbc88
+size 20797011

checkpoint_p1/milestones/checkpoint_000062048_63537152.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0110ac40e31d87f68edf2fde9a980cd71122f4ca5b937b662b76d1bd9afac5c
+size 20797011

checkpoint_p1/milestones/checkpoint_000069792_71467008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b357167a90934333410bcc4559135c874f6a5dd79310d16d9e2b49a0e3962e0
+size 20797011

checkpoint_p1/milestones/checkpoint_000077568_79429632.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d8a629b33594c9a811bc30d6f76d2eaafcc2bf65f189fd051f61343a3ef29e3
+size 20797011

checkpoint_p1/milestones/checkpoint_000085344_87392256.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339985006d95904f474369ea009710ac339cec8becc5553cbe57660555760688
+size 20797011

checkpoint_p1/milestones/checkpoint_000093120_95354880.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77459a52247edf88b50c79ff764689f5ce8760312a7f54961697ba9f4f889b51
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_privateye",
-  "experiment": "atari_privateye",
+  "experiment": "atari_privateye_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_privateye",
   "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_privateye --experiment=atari_privateye --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_privateye --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_privateye --experiment=atari_privateye_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_privateye --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_privateye",
-    "experiment": "atari_privateye",
+    "experiment": "atari_privateye_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_privateye",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_privateye_20230926_215305_073974"
+  "wandb_unique_id": "atari_privateye_APPO_20231014_045935_853351"
 }

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 sha256:2695d1182606690a5e4477af2ecce6ebb86b9de10aac625e697b97701d654ca5
-size 7656250
+oid sha256:3d6d557241dd776911a5f496883303942187bd035ace0675ee3e0f9516881072
+size 6368067