Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1696894374.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:790bc09b92ff639b6baef9fddbc6fd7ab2abf7a1b27ab43fad1a3d79d9b15cf5
+size 7809107

.summary/1/events.out.tfevents.1696894374.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a7bae1d514f9f7e9ae525ce5c5653a258e9fcebc791bea18d727f458e5677b
+size 4544314

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_centipede
     metrics:
     - type: mean_reward
-      value: 2818.10 +/- 2382.41
+      value: 5435.20 +/- 1693.19
       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_centipede
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_centipede
 ```
 
     
+## 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_centipede --train_dir=./train_dir --experiment=appo-atari_centipede
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_centipede --train_dir=./train_dir --experiment=APPO-atari_centipede
 ```
 
 
@@ -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_centipede --train_dir=./train_dir --experiment=appo-atari_centipede --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_centipede --train_dir=./train_dir --experiment=APPO-atari_centipede --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_000083648_85655552_reward_43.910.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dbb789670a02bf890d90d91100160f326b63a19b6205a416b9e15e717e19d0c
+size 20795763

checkpoint_p0/checkpoint_000098112_100466688.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8321ebed3095f613308efdc436b8bc86f3f1104f001609d8a46fb6eafa9a9a05
+size 20796099

checkpoint_p0/checkpoint_000098176_100532224.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c649c0848697fd7b57610a9006dce00b11eb2182fede9569ebd9b63ea02f8bb9
+size 20796099

checkpoint_p0/milestones/checkpoint_000008128_8323072.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e4c3b21d0aa759d047c4338287030265a98e723b4a70dc250dcb5ef1a4cccb
+size 20796955

checkpoint_p0/milestones/checkpoint_000016384_16777216.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26d9402a1716e5e23549679ce1e2474628e61d78fad4c737522d58a254d6695
+size 20797011

checkpoint_p0/milestones/checkpoint_000024640_25231360.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0354f3bc1aa2205640be73ec86bcf2653e60ec15f057b4051da8c6a5ce0072a9
+size 20797011

checkpoint_p0/milestones/checkpoint_000032896_33685504.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c58730681f7ba798c5840122b931020c277f01f0ebd59d8323de7a84861a53d
+size 20797011

checkpoint_p0/milestones/checkpoint_000041152_42139648.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1df48214dd05f3ca7efac3337dd79203b3010a73c7ccc2e9b13ece334c23ab8
+size 20797011

checkpoint_p0/milestones/checkpoint_000049408_50593792.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f84d59cdc812ad4f05665d9840d3ee07f1ddc90b8d01e0502c0cfc86ea6ce390
+size 20797011

checkpoint_p0/milestones/checkpoint_000057696_59080704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4c4e2d9ede72aec463dd33c3fea5cecd326f524306e504745bbc39cb3a670d
+size 20797011

checkpoint_p0/milestones/checkpoint_000065952_67534848.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a74758a5b2d5a1fe471b82a9fc23d7b17306fdfce99aa46cefbb5310f2a420f
+size 20797011

checkpoint_p0/milestones/checkpoint_000074208_75988992.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a960683adf91a6b9146c53b9e11f9f3ba8214b143a7fb28444a2ac16a5f00e72
+size 20797011

checkpoint_p0/milestones/checkpoint_000082464_84443136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518d0ec2341fe6d28a9f3833f929b4b173215e4c3ea49575f5db62fe266d3748
+size 20797011

checkpoint_p0/milestones/checkpoint_000090688_92864512.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6be531e3ccb079f5d64f189725c50191115fce3ef52f62b14dd5ffca4d349019
+size 20797011

checkpoint_p1/best_000094944_97222656_reward_46.010.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb2a8dda4106318a7ff39171fd89a49fea3a2971cfe6c96b6aca46eb9f0e23f
+size 20795763

checkpoint_p1/checkpoint_000097632_99975168.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e49c22ea65520bac0da11a2e38584f0c1d3b341f0e0075c6aaf2aba6eb35163f
+size 20796099

checkpoint_p1/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f09de1c1f6df9c2dc7be35def0ccf3cbefb67fce7d2c9f3ee460f34ff0424bfd
+size 20796099

checkpoint_p1/milestones/checkpoint_000008096_8290304.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cfcba79f23adbb6d64abfc371652296b299708c3a6c87ea9317ffb3af4d0f2d
+size 20796955

checkpoint_p1/milestones/checkpoint_000016320_16711680.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d0e168fcd912ec21746042924f1e79a8c434d4239c6e71e88546d8c8c30b41
+size 20797011

checkpoint_p1/milestones/checkpoint_000024544_25133056.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:967774857e8d0883b2ce6bf48b30c74392644f2b7c4e666d716ed833530dd104
+size 20797011

checkpoint_p1/milestones/checkpoint_000032736_33521664.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f9a4011ad7efdc1b700cc09704d0e4e7198703a03a661e9fb2c2d1e85bf13c
+size 20797011

checkpoint_p1/milestones/checkpoint_000040960_41943040.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642e54fe02d169652a085438289c5adf6f3a65367c69c9c646855a6484ac0c87
+size 20797011

checkpoint_p1/milestones/checkpoint_000049152_50331648.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f537930c2facbc767aacad1e2ff3c2dffeae33152318852e2fc2b8b85c00bd4
+size 20797011

checkpoint_p1/milestones/checkpoint_000057376_58753024.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b41b36ed9ac29fe31ca1561d774f8bc63a7ab4ad448a713633223c9cc3907ef
+size 20797011

checkpoint_p1/milestones/checkpoint_000065568_67141632.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5010d9bc59c23eb1f7a39c3806790e674044755d81085e320df5717ebba1bc22
+size 20797011

checkpoint_p1/milestones/checkpoint_000073792_75563008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe411b0c90597f63451a4a0e84828b6485840e23e531182910a9dc834c5b8c1
+size 20797011

checkpoint_p1/milestones/checkpoint_000082016_83984384.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac6ee23f265c57eec0cc1f693977e587d619d934723ce51b27f5c09de34bbd2c
+size 20797011

checkpoint_p1/milestones/checkpoint_000090208_92372992.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9893876e9e29b8eefce91f4ffc411ba30020566cc18b1695ccbf89119678c4ed
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_centipede",
-  "experiment": "atari_centipede",
+  "experiment": "atari_centipede_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_centipede",
   "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_centipede --experiment=atari_centipede --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_centipede --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_centipede --experiment=atari_centipede_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_centipede --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_centipede",
-    "experiment": "atari_centipede",
+    "experiment": "atari_centipede_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_centipede",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_centipede_20230925_230458_736924"
+  "wandb_unique_id": "atari_centipede_APPO_20231010_003251_687550"
 }

git.diff

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