Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697434854.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdbc2f61faa9b7eb23205d30091fe45cd639698b121db9a37c8127a6d5346850
+size 7805645

.summary/1/events.out.tfevents.1697434854.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b305e16a6bc0077e4ed5952361b17faab1f55f68785445469d60f082e972f19
+size 4510123

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_tutankham
     metrics:
     - type: mean_reward
-      value: 143.90 +/- 65.74
+      value: 262.50 +/- 30.92
       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_tutankham
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_tutankham
 ```
 
     
+## 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_tutankham --train_dir=./train_dir --experiment=appo-atari_tutankham
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_tutankham --train_dir=./train_dir --experiment=APPO-atari_tutankham
 ```
 
 
@@ -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_tutankham --train_dir=./train_dir --experiment=appo-atari_tutankham --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_tutankham --train_dir=./train_dir --experiment=APPO-atari_tutankham --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_000080064_81985536_reward_45.750.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf36f3b5be1716b313b33fe12705352d52ef7f1068349e7cf8da2c81cbca9fa
+size 20734131

checkpoint_p0/checkpoint_000096960_99287040.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc6c93fdb0fe1257b31768fa0a8810d8a25d6ac06d9203c6f86f294ac21ec835
+size 20734467

checkpoint_p0/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6098725a35dca49b843402ce49ba9f02979e36a2c8e9bb093c96ee6542da5c7c
+size 20734467

checkpoint_p0/milestones/checkpoint_000008096_8290304.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bef8d82261200767fb0e0aafb7578de58664e968939271376cbd3a5ace95ddd
+size 20735323

checkpoint_p0/milestones/checkpoint_000016352_16744448.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b3be3f9dad329a92e2ab28d508869ef8ddb75d469d060fc86f286e263e9eb4f
+size 20735379

checkpoint_p0/milestones/checkpoint_000024576_25165824.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a5c42e8758c9dd83f09806ddbede67fca7aa2e014ce29cc440f7d5991bb8c0
+size 20735379

checkpoint_p0/milestones/checkpoint_000032800_33587200.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953f0a0b79e04a986d14a74c06bc7552a76388566b419da2b35199a43f1fc7af
+size 20735379

checkpoint_p0/milestones/checkpoint_000041024_42008576.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186f8ebc2adebab816531eb47210ba009b1ec786b74b31bc4cd5e3bc2bff772e
+size 20735379

checkpoint_p0/milestones/checkpoint_000049248_50429952.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e984d28e91df154d61821f572d7e93f952c9d7e058bc496065ea01565215e9ba
+size 20735379

checkpoint_p0/milestones/checkpoint_000057472_58851328.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:385d4f1e7ac432bd10ebdf86a338ee7c591e6c71bc9169264575f20b5c86efd9
+size 20735379

checkpoint_p0/milestones/checkpoint_000065728_67305472.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e84a799b599f27d793f77531902e639b2915dc2495f6e397c0f1e56bb2a1db
+size 20735379

checkpoint_p0/milestones/checkpoint_000073952_75726848.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c816809e2efa803cb9369ed0aec4a0d32dc1a0be2af0a27ccc66d6ecc8978ff5
+size 20735379

checkpoint_p0/milestones/checkpoint_000082176_84148224.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8aead1c79a055c24683114d3f8c3f3e778f8020107d8c195411464a954d21a
+size 20735379

checkpoint_p0/milestones/checkpoint_000090368_92536832.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0bb3c3ebb6acc5fdae4a852eeed89bfbf5677dc8c40b685a25cf11aae6c238
+size 20735379

checkpoint_p1/best_000024800_25395200_reward_45.630.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd8de6eaf2d516847efcb110709f2b8010d92841dba91c09d428a36dada7471
+size 20734131

checkpoint_p1/checkpoint_000097376_99713024.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f908eb6836050e39ee8e7482269f48eaf16b2805194619fb9b84e5d4356abf6
+size 20734467

checkpoint_p1/checkpoint_000098112_100466688.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f42907090dcc6acc20245c184532f9b8e9d5abb61da2cdeee9a0c72d72a8e8
+size 20734467

checkpoint_p1/milestones/checkpoint_000008160_8355840.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12060513eda3593ec1c4a9c65c9bca7316e29b056a98b9b3b1cc08b827a3c00
+size 20735323

checkpoint_p1/milestones/checkpoint_000016416_16809984.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8beb2fec14d6ce32add45d57d58d1e2038858e71f9d1c857d5e7e39a63b1110
+size 20735379

checkpoint_p1/milestones/checkpoint_000024704_25296896.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0388d0e9e4a16be42f1b7c77f6b572271d56a3e6beb6015b9178668478352e3
+size 20735379

checkpoint_p1/milestones/checkpoint_000032960_33751040.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c40547d9523462f4821368ea47948a32eb9d616f2f6d4020012130b6f3bb9fa
+size 20735379

checkpoint_p1/milestones/checkpoint_000041248_42237952.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5406aabc63e03c1114b1e310bb7d3def96caadd440a1a869ef53c5512b4875b2
+size 20735379

checkpoint_p1/milestones/checkpoint_000049504_50692096.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6172b4e9bf798e7d66848f5afdb00aafa04316e9a7f3afb2988dc51f443d8a0d
+size 20735379

checkpoint_p1/milestones/checkpoint_000057792_59179008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83e664b506a61e46f10d9d3052e741b3392bd2db9b46de64b3932481c4ee3a71
+size 20735379

checkpoint_p1/milestones/checkpoint_000066048_67633152.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd3cedbade18ac34ae2692010cf71c252f5cd4dc02c0d94e9dee5b2d9b061ca
+size 20735379

checkpoint_p1/milestones/checkpoint_000074304_76087296.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bce7267fa57dfd3764313449e139f6d647b900988c81c651e098ef5ca51c2d7e
+size 20735379

checkpoint_p1/milestones/checkpoint_000082560_84541440.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7472221ffb1ac3b70242eae522f3118f93970648d7998a7c1406cbf83aac9d8d
+size 20735379

checkpoint_p1/milestones/checkpoint_000090752_92930048.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:627e8297ff3247e6061ac63b2da1e0c49604cacbde39a54d2a200d1762f36698
+size 20735379

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_tutankham",
-  "experiment": "atari_tutankham",
+  "experiment": "atari_tutankham_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_tutankham",
   "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_tutankham --experiment=atari_tutankham --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_tutankham --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_tutankham --experiment=atari_tutankham_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_tutankham --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_tutankham",
-    "experiment": "atari_tutankham",
+    "experiment": "atari_tutankham_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_tutankham",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_tutankham_20230927_115239_127495"
+  "wandb_unique_id": "atari_tutankham_APPO_20231016_064051_548281"
 }

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 sha256:9b002dfe7f46f0bf9bb5275161355055b76ce854525e90b87e002a8983d6fe22
-size 2160614
+oid sha256:957dc8b268d1d91db138671220441c24487a506049671b5f7d75195aef93d15a
+size 7169350