Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697197471.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0073b09fc2d4bc27be404a1e2d576170f7f0128ccdf2d376882ba63a9246cb77
+size 7896229

.summary/1/events.out.tfevents.1697197471.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5cabe9dc74bb1a8e3175ede9d6797f587799db36dff9d518ce1afb960a47d49
+size 4563762

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_namethisgame
     metrics:
     - type: mean_reward
-      value: 5368.00 +/- 1130.55
+      value: 14371.00 +/- 1723.86
       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_namethisgame
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_namethisgame
 ```
 
     
+## 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_namethisgame --train_dir=./train_dir --experiment=appo-atari_namethisgame
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_namethisgame --train_dir=./train_dir --experiment=APPO-atari_namethisgame
 ```
 
 
@@ -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_namethisgame --train_dir=./train_dir --experiment=appo-atari_namethisgame --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_namethisgame --train_dir=./train_dir --experiment=APPO-atari_namethisgame --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_000071968_73695232_reward_209.840.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218b73d3f8662f27214200e3265e4b52e1560f30c3ea0e7902cda05c7beda17b
+size 20721843

checkpoint_p0/checkpoint_000097536_99876864.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20fab3b5cae71895cf46d73520fcc35e8292fba485b711c77f84baac705b56fc
+size 20722179

checkpoint_p0/checkpoint_000098016_100368384.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1453d38f22f92ace4c85f1ff7c0980a2265b82c65c389efaf30c0d1c9ef6c0c8
+size 20722179

checkpoint_p0/milestones/checkpoint_000008032_8224768.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c11b7d662dcab6a919147928123e8791d2ea04c43f3bc1f88feac20bb6a5a9a
+size 20723035

checkpoint_p0/milestones/checkpoint_000016128_16515072.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c7b125f6b35ffcf87e876363dca7eba267ae1086064f1cad1e8293999b1f86f
+size 20723091

checkpoint_p0/milestones/checkpoint_000024256_24838144.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ac6eb8e7ae1c7cac14a23eac1dd68285f438f0a1d2f2dfd0a9208c24acc9e9
+size 20723091

checkpoint_p0/milestones/checkpoint_000032416_33193984.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fa5d25122c396b64b721cc6421eb1412c4b52c9844a4b954b12c7c99109b13d
+size 20723091

checkpoint_p0/milestones/checkpoint_000040544_41517056.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d2dfc5b3ed921911b516021032b2238a33f846be6e128a33325baaa94a57a5
+size 20723091

checkpoint_p0/milestones/checkpoint_000048672_49840128.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19814ca012895ad4435e8d134ce4b65fd37bb0b98d45be8632c6230a95b2bcc1
+size 20723091

checkpoint_p0/milestones/checkpoint_000056832_58195968.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06cdc38aeb0438a5ee7387d3e75d74a6208b28ca8b11cc69f73604070bfd729f
+size 20723091

checkpoint_p0/milestones/checkpoint_000064960_66519040.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f6adf8ca96d74d0fbadf5ad0b4dc470d29ade007fa5452fb7458df28ad31c7
+size 20723091

checkpoint_p0/milestones/checkpoint_000073088_74842112.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e72f0ab1006f42bc6e2e1874e696d94346761dd6de22ee61f5d04792933801dd
+size 20723091

checkpoint_p0/milestones/checkpoint_000081216_83165184.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9706d92de61ccec40628771e1683a12eca7863c4131294fce9d98d4c4d794066
+size 20723091

checkpoint_p0/milestones/checkpoint_000089376_91521024.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b071fd57df7ec9ee3e4b93d8549239aabf260394c866c08c1aa53d7711b5a8
+size 20723091

checkpoint_p0/milestones/checkpoint_000097536_99876864.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bec02b7fd5ae62dee9d9ce178fc1af7211aaaa59944693a8439c57a4f272cfb
+size 20723091

checkpoint_p1/best_000087200_89292800_reward_200.470.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36576d2b1f595bec3a2a449dec62a82479bd832b68f4d53d630395e75517b2f9
+size 20721843

checkpoint_p1/checkpoint_000097184_99516416.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e2b0f1de1f068bc6d32e311b199c5c43e230647d82a90adda88eb3c36a8f93
+size 20722179

checkpoint_p1/checkpoint_000097696_100040704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992e8239750bc2291926ed43bf84814f4edfbe27273a6e73bdaadd2532315720
+size 20722179

checkpoint_p1/milestones/checkpoint_000008000_8192000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ce80f86030aace50809f239a703c692f4089c5f2cfe581e9ce0451c6bec758
+size 20723035

checkpoint_p1/milestones/checkpoint_000016096_16482304.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72f4beaf2c300c2fc045d059e2c94e10a6a8a8836bb5fb2fc33f6ca3f5a4125
+size 20723091

checkpoint_p1/milestones/checkpoint_000024192_24772608.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f99deda34738fc5937dfa126156bd0f74ac44ba0fe8c9d1a224368bd9a4c7fa
+size 20723091

checkpoint_p1/milestones/checkpoint_000032320_33095680.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a2fd70749586df532d298b6aabdb0cb616b4ae6f197be3e0c65747a5eb1417a
+size 20723091

checkpoint_p1/milestones/checkpoint_000040416_41385984.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bedd56a362b7d0cf8be4fe47f362f68b559539155c257a75a82cad60f6a8dedb
+size 20723091

checkpoint_p1/milestones/checkpoint_000048512_49676288.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd13c5180130b8d26084508d9418d3d1b131f8b44b3e2c558a49a88255a46c7
+size 20723091

checkpoint_p1/milestones/checkpoint_000056640_57999360.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a60576691ecb5c662a55ee6635ce83b6dfa527035edf5a9c495b1890d48bf1f
+size 20723091

checkpoint_p1/milestones/checkpoint_000064768_66322432.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566a720412edea2a92a0036e33cafca1055941e4908b5183738a192ec97044b8
+size 20723091

checkpoint_p1/milestones/checkpoint_000072864_74612736.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c3a4becba7c2ec9682293034302c419ae55f39b25da4631f307867865543ad3
+size 20723091

checkpoint_p1/milestones/checkpoint_000080960_82903040.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad8fc5fbdfd368648e2ec0223fe3a4b8a9321a1e854dba29591c562aa0bbe2e
+size 20723091

checkpoint_p1/milestones/checkpoint_000089088_91226112.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b15cc1d0bf5548b4a897bdac44f70eb5a82a3b0bfe4119b876cbde08c1f5fc5
+size 20723091

checkpoint_p1/milestones/checkpoint_000097184_99516416.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0bdb62c3e0c0f3841858727c481ef599cb5df2bfddebcf149ad0f00f5a6db5f
+size 20723091

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_namethisgame",
-  "experiment": "atari_namethisgame",
+  "experiment": "atari_namethisgame_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_namethisgame",
   "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_namethisgame --experiment=atari_namethisgame --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_namethisgame --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_namethisgame --experiment=atari_namethisgame_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_namethisgame --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_namethisgame",
-    "experiment": "atari_namethisgame",
+    "experiment": "atari_namethisgame_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_namethisgame",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_namethisgame_20230926_180424_211471"
+  "wandb_unique_id": "atari_namethisgame_APPO_20231013_124429_010470"
 }

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 sha256:181a717d07202524bb7cf542b9176d6d3ca667bcdb95bf18658face221e421c3
-size 12244414
+oid sha256:262f5caa25a3349a82197ed93c3709101a68885aaf0ce8baac616ab861587fe1
+size 21157952