Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697420737.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e15874fb0863beb53c3274deb17b3169c1c09065489cc53cdf9fa8c54f0a43f
+size 7662829

.summary/1/events.out.tfevents.1697420737.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8798a1c50954eb284f26cb684d4154045d6b1cdfb545ba79660b105f123dcd84
+size 4435165

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_timepilot
     metrics:
     - type: mean_reward
-      value: 5050.00 +/- 1786.76
+      value: 15050.00 +/- 1467.82
       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_timepilot
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_timepilot
 ```
 
     
+## 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_timepilot --train_dir=./train_dir --experiment=appo-atari_timepilot
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_timepilot --train_dir=./train_dir --experiment=APPO-atari_timepilot
 ```
 
 
@@ -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_timepilot --train_dir=./train_dir --experiment=appo-atari_timepilot --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_timepilot --train_dir=./train_dir --experiment=APPO-atari_timepilot --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_000090752_92930048_reward_9.360.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e02d1452f9495d79a0a83c96e8f9fd1628dfb4878b297676db94cab10650dc3d
+size 20746419

checkpoint_p0/checkpoint_000097344_99680256.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b1e5fe1641e6a76ec942fc59809eaeb0768e6f5e903915433fa3139aad1d9c
+size 20746755

checkpoint_p0/checkpoint_000097984_100335616.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0893a54ddfb702e40f528e82dc07ceeb44a6760e7cc3709bb822b3a739d6e6f2
+size 20746755

checkpoint_p0/milestones/checkpoint_000008256_8454144.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7dd8aef909c3c6cc6cafe15e549d8d99d1ce12e83ca7da19bba0428ed6a05d
+size 20747611

checkpoint_p0/milestones/checkpoint_000016640_17039360.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2be463481d5aac43eb35e966bc5c2ee52f901624920b7af38414f10e5df0518
+size 20747667

checkpoint_p0/milestones/checkpoint_000025024_25624576.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b621199f20b14186cd637500cd305569dbaf03bf253f092260db22fc35f6afc3
+size 20747667

checkpoint_p0/milestones/checkpoint_000033440_34242560.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a0207c173facf94d7a09ec23750738fe4e8776242785d013d4b8232b297d438
+size 20747667

checkpoint_p0/milestones/checkpoint_000041856_42860544.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6289165c3c8b9df2ba3e34082d1d20e68ab860fccee242eba567e5d8657fe25f
+size 20747667

checkpoint_p0/milestones/checkpoint_000050240_51445760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4f1738f112dd9d6fcb6c460346b41909fa848efa32668b8994ee1ab738b052
+size 20747667

checkpoint_p0/milestones/checkpoint_000058656_60063744.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb6ea3aac56104fc9a27789f15145688d6f65d08448f61cdae3f3dfcb02ed30
+size 20747667

checkpoint_p0/milestones/checkpoint_000067072_68681728.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d646b02dc500b6d27b35618f8485ff69e906db15bae5aba1bd40d3a4816eda
+size 20747667

checkpoint_p0/milestones/checkpoint_000075488_77299712.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad0cf569faea69dad07353d5055fa4eff90f77957df7dbf6e9b53aed1a35bd2
+size 20747667

checkpoint_p0/milestones/checkpoint_000083904_85917696.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3717822d25b97d874cb55c7eb6d7c67a3a420723ba7da649e158c639100e1df2
+size 20747667

checkpoint_p0/milestones/checkpoint_000092288_94502912.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91df7f2105e071f7dd9b44adf02a9af54e50a69de10bfeb84fd39fff3d94bf9d
+size 20747667

checkpoint_p1/best_000096384_98697216_reward_10.360.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b24a9199959f220ba9733033807809beba5eb688b51b0e0ea3a4d003d617169e
+size 20746419

checkpoint_p1/checkpoint_000097024_99352576.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed6e160615726ca198e0fb54282e1c07cc5ca56a211780bda00f7e3827755545
+size 20746755

checkpoint_p1/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae4ba59726c30e4760b1f30433b72ff9bd4b58844b61bdbc0365d77be2875d8
+size 20746755

checkpoint_p1/milestones/checkpoint_000008224_8421376.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a1940cf89640e708805ee498c05d0d344aac2445bf3761561d63393ea2741a7
+size 20747611

checkpoint_p1/milestones/checkpoint_000016544_16941056.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d016d844620a3d36384842fbda9fb527495a1ba61c1cc69b10092ee9ac1031
+size 20747667

checkpoint_p1/milestones/checkpoint_000024960_25559040.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76fa23cedc839977840cd45bd5d7a9fbfb399e32039726c890e67039b73204e3
+size 20747667

checkpoint_p1/milestones/checkpoint_000033312_34111488.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a3722b38c423de0e5d244b042d4b7557cb052d6f653a58e24e13c58eac7a61e
+size 20747667

checkpoint_p1/milestones/checkpoint_000041696_42696704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2304fb43094c3fdfcdd9292f9a8ea2c0a51003631446b640ca152c1b087d9976
+size 20747667

checkpoint_p1/milestones/checkpoint_000050080_51281920.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad9646ae52ebf3105e5f6061d5fa2f93a878821332137e85a6d07d43fc5a114
+size 20747667

checkpoint_p1/milestones/checkpoint_000058432_59834368.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2061ae14f8f1d4b3356ee378a67b0cd52ff79d003a79d6d0fb9b2fe3459d59
+size 20747667

checkpoint_p1/milestones/checkpoint_000066848_68452352.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe18180f6e9412946b93519fe151025fba19337bfdde2596aa98621ec8055c3
+size 20747667

checkpoint_p1/milestones/checkpoint_000075232_77037568.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d654cb302f775f1729cbe51bcf80d34e09e7a1ff2022946aa25672632af7af
+size 20747667

checkpoint_p1/milestones/checkpoint_000083616_85622784.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c08f1e07b77b9cac036a8b38cb8f0d35130e888c1fb08b98279bd7044bcf5939
+size 20747667

checkpoint_p1/milestones/checkpoint_000092000_94208000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:227f75b7f03a9b9e41858bcd5390091f4d317ff8e46909130a94725a5cf4b64c
+size 20747667

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_timepilot",
-  "experiment": "atari_timepilot",
+  "experiment": "atari_timepilot_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_timepilot",
   "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_timepilot --experiment=atari_timepilot --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_timepilot --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_timepilot --experiment=atari_timepilot_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_timepilot --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_timepilot",
-    "experiment": "atari_timepilot",
+    "experiment": "atari_timepilot_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_timepilot",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_timepilot_20230927_105842_697630"
+  "wandb_unique_id": "atari_timepilot_APPO_20231016_024534_717006"
 }

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:e5b886eb35c162c337ab6d87fa7335847ecc1b0a6c5f4d68ad2d1e390a019832
-size 2642730
+oid sha256:1e1f760838ec6ca924273e03703fe894bc5b74ea1d1bfebb7a171f10da200770
+size 4076763