Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1696820851.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7362d86ae6c23586ceca9dc4d98f8c60245cb78ecd549423d6238e2734e189
+size 8019896

.summary/1/events.out.tfevents.1696820851.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ef01d4349c47eab61b423aa1c6dcfb57859eb5d2a23ed810a675afabce0a57
+size 4645004

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_beamrider
     metrics:
     - type: mean_reward
-      value: 550.00 +/- 86.33
+      value: 7105.40 +/- 2931.13
       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_beamrider
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_beamrider
 ```
 
     
+## 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_beamrider --train_dir=./train_dir --experiment=appo-atari_beamrider
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_beamrider --train_dir=./train_dir --experiment=APPO-atari_beamrider
 ```
 
 
@@ -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_beamrider --train_dir=./train_dir --experiment=appo-atari_beamrider --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_beamrider --train_dir=./train_dir --experiment=APPO-atari_beamrider --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_000093792_96043008_reward_41.570.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd6f929e8e3050ce836f7bc890ed2093ca69a5b6d2fb5bf0f7bc80128353555
+size 20740275

checkpoint_p0/checkpoint_000097344_99680256.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf15979bd57b31a05e65351b426e17e0f30c73178c45fd2cb260969999b3b69
+size 20740611

checkpoint_p0/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4591ca1cabda604ed3f08f3192887886b372ab41ee4cd37775f5df6446903a98
+size 20740611

checkpoint_p0/milestones/checkpoint_000007904_8093696.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b772a8693fda3c1cbbdeb9ef22f2c275a2d6b3d2579c93da47d2e9d83e9bc2b6
+size 20741467

checkpoint_p0/milestones/checkpoint_000015872_16252928.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ada809150ce1d470fa5ffa1bd61c77a1542ea1ca6d3f060828d742d0eb2bca7b
+size 20741523

checkpoint_p0/milestones/checkpoint_000023872_24444928.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37fdbab1e97aa40080d6a3ef67ae36c53f3a8f2732991cf14e6b6e08e198934
+size 20741523

checkpoint_p0/milestones/checkpoint_000031840_32604160.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58bcc154e235b42230a2a77c9bfb5b1a6c84f44643a55fc81ccdafa80defacae
+size 20741523

checkpoint_p0/milestones/checkpoint_000039840_40796160.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef7bef446fb55426022cbe3d35929b10f27a9dd11d847977477d56c090f1ccf
+size 20741523

checkpoint_p0/milestones/checkpoint_000047808_48955392.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4001234168ff892a41694a32ed9ab14abbc7e1842c9975fea744e5911f672a54
+size 20741523

checkpoint_p0/milestones/checkpoint_000055808_57147392.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74815a68302f85ddde3d2ce064927a6423d10a8c0b93ff8e2258828b8a875763
+size 20741523

checkpoint_p0/milestones/checkpoint_000063808_65339392.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2296578fe732af280207783beefd0114b9f0704a2cc729293de24658a21af417
+size 20741523

checkpoint_p0/milestones/checkpoint_000071808_73531392.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fafc48c2f162989dfc3dd6a197dd297b4d68869cd46b62fbd326542fb032d08
+size 20741523

checkpoint_p0/milestones/checkpoint_000079776_81690624.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:786fab8a815cdb369cc9541f00d4dc400a6088f1dd946c034a38e59bef02a0fa
+size 20741523

checkpoint_p0/milestones/checkpoint_000087776_89882624.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5616ddf79efeaa7bc888b28903b500759a45847e57a6de99577fb84b76f7dd0
+size 20741523

checkpoint_p0/milestones/checkpoint_000095744_98041856.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638b6be15d652e2efeb0c703295f494d9f71148325c65daf91d5e2943b9e432c
+size 20741523

checkpoint_p1/best_000090432_92602368_reward_39.550.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdbe689f1c3b4e12232ee3ebb571796ede6bef4869eedb9e93678a64548a10c3
+size 20740275

checkpoint_p1/checkpoint_000098464_100827136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cbc567f1f3c05221e1e97942ac30154f7305559a0610bfb06d6dbf72f09eaea
+size 20740611

checkpoint_p1/checkpoint_000098784_101154816.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60dec3b235cb2e92a97bbd90fa5ea58d126978a54e12e949e5f08f896f1168ff
+size 20740611

checkpoint_p1/milestones/checkpoint_000007968_8159232.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974b99a2716ca84a77f08286011257140608a9ca9cc81ed17237bf09fecbb6dd
+size 20741467

checkpoint_p1/milestones/checkpoint_000016032_16416768.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7db2171703e14d718935e3d2b80cd5a22caadd75578d6c28f304ddeb4c940d0
+size 20741523

checkpoint_p1/milestones/checkpoint_000024128_24707072.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f91f37d413b56b761803c50ce1fa63df64b7cadbab4d98235b320b69e89697
+size 20741523

checkpoint_p1/milestones/checkpoint_000032192_32964608.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3451241775acbc04f104e8b1bdc274a873efe69e807c6f688dd132a377c0794c
+size 20741523

checkpoint_p1/milestones/checkpoint_000040288_41254912.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:214359c90825ec650d1cae8070032a6268f1551ed779c828bf68fd3618321c87
+size 20741523

checkpoint_p1/milestones/checkpoint_000048384_49545216.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf927dff7eaee7dcc8c757f19d952528d3623d7efd638735c0b5218f25354cbb
+size 20741523

checkpoint_p1/milestones/checkpoint_000056448_57802752.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3806932d775d0bf009d2005f6e3164051689198135e57ef36c05388cc9d7eed
+size 20741523

checkpoint_p1/milestones/checkpoint_000064544_66093056.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b72e641648c40e1413f896b329c38c5e6a92825790228561a6e6a2334d4c329
+size 20741523

checkpoint_p1/milestones/checkpoint_000072608_74350592.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6476db6165e05e66862dbfe38ea48176c45fe444d7a93f355c59718d22af1399
+size 20741523

checkpoint_p1/milestones/checkpoint_000080672_82608128.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b287b0f081db8463eaf7cc8769041f61ddfc5c96ee770c3d8501bd25a901fc
+size 20741523

checkpoint_p1/milestones/checkpoint_000088768_90898432.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:266cd456c6b0230f55898ddf66cb29cd1b7131ebb95475ba466ff2b7b2be7b18
+size 20741523

checkpoint_p1/milestones/checkpoint_000096864_99188736.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:022cea07e9bc8af6c95ae96b3f49339613560dd3b6c259ee46e29b013ad40209
+size 20741523

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_beamrider",
-  "experiment": "atari_beamrider",
+  "experiment": "atari_beamrider_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_beamrider",
   "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_beamrider --experiment=atari_beamrider --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_beamrider --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_beamrider --experiment=atari_beamrider_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_beamrider --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_beamrider",
-    "experiment": "atari_beamrider",
+    "experiment": "atari_beamrider_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_beamrider",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_beamrider_20230925_201508_276248"
+  "wandb_unique_id": "atari_beamrider_APPO_20231009_040728_476822"
 }

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:cf78ebefce98d2ed24463f365e952edb24143855d16a515555682269cdc9365b
-size 8980259
+oid sha256:1cb49473c602f7d682d0503b509f4c91414ceb33f30e084ccbc5976243d2eb78
+size 24413627