Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697316360.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64277732c25ae7834232eb3f4740e3d51cf7e8fdb139452f495ebf2ff84c1d07
+size 8408218

.summary/1/events.out.tfevents.1697316360.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1027e1304f45ae3166abedb5207eeb35997e42fe8ad1792cabb767976cded673
+size 4845831

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_robotank
     metrics:
     - type: mean_reward
-      value: 4.20 +/- 1.54
+      value: 60.00 +/- 6.96
       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_robotank
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_robotank
 ```
 
     
+## 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_robotank --train_dir=./train_dir --experiment=appo-atari_robotank
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_robotank --train_dir=./train_dir --experiment=APPO-atari_robotank
 ```
 
 
@@ -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_robotank --train_dir=./train_dir --experiment=appo-atari_robotank --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_robotank --train_dir=./train_dir --experiment=APPO-atari_robotank --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_000088640_90767360_reward_9.020.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa28594b0bbc33b8a42d5ae4207c62adaa561be80c156e038914ab3f0058795
+size 20795763

checkpoint_p0/checkpoint_000097344_99680256.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed6cbcd9150cf39cffa858a7a31717b03d4be6af9a1696056dbfe459549aacc8
+size 20796099

checkpoint_p0/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d44fd1750f7913f8bfa17c7fe40ad46fbd42c1cecd104fad26fd44d542df669
+size 20796099

checkpoint_p0/milestones/checkpoint_000007456_7634944.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be61f09b831150561ed7f2e91fe6f1dccdfff8b918af815a242c5e00693d8f98
+size 20796955

checkpoint_p0/milestones/checkpoint_000015040_15400960.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13f54719f689d50511f5c3562966f17bcb6c650023660a8bc5b4a7461807512
+size 20797011

checkpoint_p0/milestones/checkpoint_000022656_23199744.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:678266254842f1cb7123d86d885083f982adf87b0a28004974fd07e953b1e0dc
+size 20797011

checkpoint_p0/milestones/checkpoint_000030272_30998528.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1aa9decb24838d13aef7383cf1a4b2bab27039e159a59172711da48286a83cc
+size 20797011

checkpoint_p0/milestones/checkpoint_000037920_38830080.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5446079f5abaff16f9676e7690176105c97ef1112bdddb565afd00d55ed871d1
+size 20797011

checkpoint_p0/milestones/checkpoint_000045504_46596096.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55bdae1812af007a7a462a410b1fd87e0ad659f025efdd0ba5e67ea943a6085
+size 20797011

checkpoint_p0/milestones/checkpoint_000053120_54394880.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6bc6d30635b66395f63917eac6cf2e8859df4f9f91de80eea515079fb349173
+size 20797011

checkpoint_p0/milestones/checkpoint_000060768_62226432.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad98e790cf5043dc02cbe226ed16c2860c526cd4027fe4a2bceaf9083a74b0b
+size 20797011

checkpoint_p0/milestones/checkpoint_000068384_70025216.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cc4b46ee81605a6bc55b200164a7ea57c6d50ae8d4fd14a9c1c64914b53d394
+size 20797011

checkpoint_p0/milestones/checkpoint_000076032_77856768.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e496c4cb59a8d6c0cb5c11117880831f396f36245ad0cca8ef87312794974aec
+size 20797011

checkpoint_p0/milestones/checkpoint_000083648_85655552.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48023057daa92e715aca43e1b131431b28919af6ab90afe3010b27cf06c7f36d
+size 20797011

checkpoint_p0/milestones/checkpoint_000091264_93454336.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1396ad3da2a5eab20c81e46d1e12f3afbbf7f0677c983eed71fb9c416da7c1c
+size 20797011

checkpoint_p1/best_000090400_92569600_reward_8.970.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb3e3e6c5f09e9d195013d92dd24b0cb527748866e8726d5beefd96595fa48e
+size 20795763

checkpoint_p1/checkpoint_000098240_100597760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4bed961997b0e5732065d98d6f7f26d36e4e6e626337e299fdd91ad197d7079
+size 20796099

checkpoint_p1/checkpoint_000098560_100925440.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a1d1c353da7e7fa24c2e1e33db6b453215a16e09610967ff149253693adb64
+size 20796099

checkpoint_p1/milestones/checkpoint_000007552_7733248.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc5e82ae564036f07e7d74b2e197103951665ff8930d8ef92c5fad4712490ff
+size 20796955

checkpoint_p1/milestones/checkpoint_000015200_15564800.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a879058751a58eb332f760f527a819260615fc2452ef30b5a13a77cde0b7eda
+size 20797011

checkpoint_p1/milestones/checkpoint_000022880_23429120.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd2afce26e4bd60e35f3d2484ff87c756d8875aa19e675aa79118e687020707
+size 20797011

checkpoint_p1/milestones/checkpoint_000030560_31293440.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d632d132babdca738fd3beefbdf7721851a6b9009a0554221d8810a52d70b41a
+size 20797011

checkpoint_p1/milestones/checkpoint_000038240_39157760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000ace85b789ac9ccef8e203cfb089af32a3dff9bdbb29fcd03221ea614cc96e
+size 20797011

checkpoint_p1/milestones/checkpoint_000045920_47022080.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e5addffab28710da21769eec467d262485e0a7a990cc8c6aeb1f8a778f6c4ec
+size 20797011

checkpoint_p1/milestones/checkpoint_000053632_54919168.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c2f1131c95c26c1459138d5c11937b0aecbd6520ac787f0721d55dae4774aa
+size 20797011

checkpoint_p1/milestones/checkpoint_000061312_62783488.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af8dbd326fb2714d79090187a8f03e9c85cc5b5a325155380ef5210da436a06
+size 20797011

checkpoint_p1/milestones/checkpoint_000068992_70647808.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7d06931b30c88d5a8163885b051adfbc3798b0708d99179fbdaf7b0fa82e6f
+size 20797011

checkpoint_p1/milestones/checkpoint_000076704_78544896.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8d39b150e21bb18af567d0a967b6ea9fc430a9d988b36bf7479bd89e909e8e
+size 20797011

checkpoint_p1/milestones/checkpoint_000084416_86441984.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e948fb59e423f469942cdc3eadb48e7401d5124f9ee960c8ab4ae681f044f6f8
+size 20797011

checkpoint_p1/milestones/checkpoint_000092096_94306304.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417eb129a1c7d0faba94d115f566c7ec367ab720fc2453af0ffb4bcb812c9d3f
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_robotank",
-  "experiment": "atari_robotank",
+  "experiment": "atari_robotank_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_robotank",
   "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_robotank --experiment=atari_robotank --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_robotank --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_robotank --experiment=atari_robotank_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_robotank --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_robotank",
-    "experiment": "atari_robotank",
+    "experiment": "atari_robotank_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_robotank",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_robotank_20230927_013456_484279"
+  "wandb_unique_id": "atari_robotank_APPO_20231014_214558_044715"
 }

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 sha256:1c4d4794c3f7a48b18efed3bb1aa67fa31d4ed778ddb52828208f5bdba5ff3a8
-size 9044087
+oid sha256:530cd09fadba49cb80e6545a4ebb250660bace537622cb5cde20579a3fca26ad
+size 21908488