Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697032456.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b96922927bfde3a297e03f360e78815e2996bf1a8ef9ee3fb5d39ce9ac77d8
+size 8212696

.summary/1/events.out.tfevents.1697032456.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc55b8020d4460cd46c0dabe57f50aaf681624ae6e402119a75ae987b8895c8
+size 4737721

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_frostbite
     metrics:
     - type: mean_reward
-      value: 261.00 +/- 13.75
+      value: 3718.00 +/- 392.42
       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_frostbite
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_frostbite
 ```
 
     
+## 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_frostbite --train_dir=./train_dir --experiment=appo-atari_frostbite
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_frostbite --train_dir=./train_dir --experiment=APPO-atari_frostbite
 ```
 
 
@@ -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_frostbite --train_dir=./train_dir --experiment=appo-atari_frostbite --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_frostbite --train_dir=./train_dir --experiment=APPO-atari_frostbite --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_000091072_93257728_reward_49.420.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50bd790e349c387088da40ed7885913a8d0520ca1a6ce1a1fcb08a0baf18f24c
+size 20795763

checkpoint_p0/checkpoint_000097568_99909632.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf4da47205e0eba8a7300ab3884a771598c51e335ea6bf3f79ca0e2b75bbd891
+size 20796099

checkpoint_p0/checkpoint_000097696_100040704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f47348b77e8fb64d3571d1c88621963835d087292dc84e9786f7a31807cf2b
+size 20796099

checkpoint_p0/milestones/checkpoint_000007680_7864320.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4181f251310259c393e4f6d7fd473c59d536b60d522c0ebf2ca1b51f334b8636
+size 20796955

checkpoint_p0/milestones/checkpoint_000015456_15826944.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c249faf97f8ad5511d49cbed544899320bc1e02753dcf6910b76d42130efc966
+size 20797011

checkpoint_p0/milestones/checkpoint_000023232_23789568.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cbb4fc9f8a8d0a25bff5a1783e0ac5dcb1fe06e04e822e172da5871c187c06d
+size 20797011

checkpoint_p0/milestones/checkpoint_000031040_31784960.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae0ae3ee4989b6e9059e208b5d008489049427bb58a9843715262a03e8ceb6a1
+size 20797011

checkpoint_p0/milestones/checkpoint_000038848_39780352.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef39ea203713392a0c304debd6973a44bb8c82cb3423ae2e98869ec7281c9c1
+size 20797011

checkpoint_p0/milestones/checkpoint_000046656_47775744.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3e5bddb9f98058518a86f07427619cfff6adb41c70188433ef97076214191d
+size 20797011

checkpoint_p0/milestones/checkpoint_000054464_55771136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:510c85d014cd6c493e4e1375c1430f952e8fab552e8273ba032d3f775494db34
+size 20797011

checkpoint_p0/milestones/checkpoint_000062304_63799296.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1a34d573f7848e94c472839eb6129a60688f97de9b738a62cb532bda231121
+size 20797011

checkpoint_p0/milestones/checkpoint_000070144_71827456.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e9291d29013bcd5ae76d99a250cc44488c34eacf900d6b9ab5b10a2a3010b6
+size 20797011

checkpoint_p0/milestones/checkpoint_000077984_79855616.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e115ff1eabaf99215623f08b936f0510de093a12845e0288988ad4912a1d724
+size 20797011

checkpoint_p0/milestones/checkpoint_000085792_87851008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8c0bdbd21b428769b44b9609ec3e149354e9f48edbdec047556d218dc604ce3
+size 20797011

checkpoint_p0/milestones/checkpoint_000093632_95879168.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993bf56216e0ffb4ac4658c7ce12f92e3465398fadd62407766a7094c2bcdf52
+size 20797011

checkpoint_p1/best_000073376_75137024_reward_49.840.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85c291474d95bfc738fa87ebfda541e5f959a68850587a9504ab51645871cd63
+size 20795763

checkpoint_p1/checkpoint_000098976_101351424.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbda69b4f53355807d6f4730c8a8b9f77f84e529cc8548718dd6b9bbca399f91
+size 20796099

checkpoint_p1/checkpoint_000099104_101482496.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd1c18ebfcf32dd2dd415ba05bea48b27a87216b0aae7a753ef396fbd1a32df
+size 20796099

checkpoint_p1/milestones/checkpoint_000007776_7962624.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5ad1c06c0b4b7d16447893eee4ebcc9cc83383c73f7a2786f6a218dc2dea19
+size 20796955

checkpoint_p1/milestones/checkpoint_000015680_16056320.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c857f0e6423070101fa42bc95718e67c6ed3346f800f3e1df674d4eca9142e6
+size 20797011

checkpoint_p1/milestones/checkpoint_000023584_24150016.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:273ae43d63b2bc15f1ecedb2029371e81edaa62654935d700342294b94b59f3e
+size 20797011

checkpoint_p1/milestones/checkpoint_000031488_32243712.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31249c139bea7060e31232063fe5f774915ee0d2c3d2725e938c69208515caa8
+size 20797011

checkpoint_p1/milestones/checkpoint_000039392_40337408.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:480e5058c7a7ed95e539bd53bb3c6061f184194d023e463009bae838cdd13a4f
+size 20797011

checkpoint_p1/milestones/checkpoint_000047328_48463872.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26c67a600f9526fef5fe1bf0ae6a17bcd3e0ffa92ec86b2f3cf53e6af6de532
+size 20797011

checkpoint_p1/milestones/checkpoint_000055264_56590336.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e1d7cb5c558dc6103554ec7fb6f17de25960cb92c8afbbaba2bbe08c25d3ad
+size 20797011

checkpoint_p1/milestones/checkpoint_000063232_64749568.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6481f8381ee95bbf289d763214d60730d4638ddc38b54a82f3e1e5c87de2dbb
+size 20797011

checkpoint_p1/milestones/checkpoint_000071168_72876032.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f464dcbbb6d5fecab4e391a8d02b149280d4904ba68bce9014b4f9414b871d19
+size 20797011

checkpoint_p1/milestones/checkpoint_000079136_81035264.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c26587b89808b7eda3e44ac2c3840476266958129280393031d0be3e3dc6e3
+size 20797011

checkpoint_p1/milestones/checkpoint_000087072_89161728.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf6689e2e2cb22185e25f212724c9ce1cfabd2b2b0081a5f1ee12c36c4f228b3
+size 20797011

checkpoint_p1/milestones/checkpoint_000095008_97288192.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e50e4971f81e586ae04835e6e9894fdf83ea7526b1512d5034ee42eb06982f
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_frostbite",
-  "experiment": "atari_frostbite",
+  "experiment": "atari_frostbite_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_frostbite",
   "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_frostbite --experiment=atari_frostbite --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_frostbite --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_frostbite --experiment=atari_frostbite_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_frostbite --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_frostbite",
-    "experiment": "atari_frostbite",
+    "experiment": "atari_frostbite_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_frostbite",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_frostbite_20230926_074710_573171"
+  "wandb_unique_id": "atari_frostbite_APPO_20231011_145413_028194"
 }

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 sha256:81ed72d61873668eef83641be80c9fcecb7233d7b1e7330be51212def9618067
-size 1313662
+oid sha256:e7901fa77485ce5c1745db65d37929b81475e6f3bef55a7b777369b39c8273c8
+size 3267790