Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697121858.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e78680873e9956c245ce9449351e468b2abcfcb41898cce841e215107f0343
+size 8148863

.summary/1/events.out.tfevents.1697121858.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c95911a28fcf43e4c5fd401b397ecc700a6e3a153358d73c3c5a514f8e7527
+size 4722267

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_kangaroo
     metrics:
     - type: mean_reward
-      value: 1760.00 +/- 120.00
+      value: 12390.00 +/- 1431.40
       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_kangaroo
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_kangaroo
 ```
 
     
+## 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_kangaroo --train_dir=./train_dir --experiment=appo-atari_kangaroo
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_kangaroo --train_dir=./train_dir --experiment=APPO-atari_kangaroo
 ```
 
 
@@ -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_kangaroo --train_dir=./train_dir --experiment=appo-atari_kangaroo --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_kangaroo --train_dir=./train_dir --experiment=APPO-atari_kangaroo --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_000096640_98959360_reward_25.770.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c67cb2a3bcc9d0eb6afe2e28c854574e08a483d7b7bac400ec614f2f892d1fc9
+size 20795763

checkpoint_p0/checkpoint_000097440_99778560.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d1ed2dd82c89745560be8a524e48cfa0ae5b16e85af6bbced263368cdd534f0
+size 20796099

checkpoint_p0/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce2aee791f1a3fd24d89db13bcc991bfd8c36c89bfced8a187fd67998b35e79b
+size 20796099

checkpoint_p0/milestones/checkpoint_000007776_7962624.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4bfce5d222236ad2850c9c6a47f51922cd412d5d288d32373a0e839d85df211
+size 20796955

checkpoint_p0/milestones/checkpoint_000015648_16023552.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5012ee051ef4639fc6a066484593326be557e4f1ef490b010b6193b20a6f3514
+size 20797011

checkpoint_p0/milestones/checkpoint_000023520_24084480.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90cc2f5eb938b4a543a8b75021ab33dc80ef8ebc3f3cab2ab38d497a37f32297
+size 20797011

checkpoint_p0/milestones/checkpoint_000031392_32145408.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0cf11b323c137f108f77a3a6b0557b73c75ea5875ca897bc16f6cbbad209e9b
+size 20797011

checkpoint_p0/milestones/checkpoint_000039264_40206336.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ea8d84151dfaa4bbc509fb1c43a1ee31ed94621ac61fed16b5f31ce35cce97
+size 20797011

checkpoint_p0/milestones/checkpoint_000047136_48267264.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3522806781eca35b757bd1e83637723e40a38ab1c009648b570c3a284b4704f2
+size 20797011

checkpoint_p0/milestones/checkpoint_000055008_56328192.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:797da1e28509af88bfca63fe08cfee1a8ed65ac84e5acda1aedf66e1d8ce3f08
+size 20797011

checkpoint_p0/milestones/checkpoint_000062848_64356352.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1793fb3a4ce81dd173bfe3ea550fdef6afad0a2b706c542eb1e05c9f807a846d
+size 20797011

checkpoint_p0/milestones/checkpoint_000070720_72417280.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3adb34eae25baa416088a4b93950bfa8ed1c9fd8ec0240ad7e72a002d2844e6
+size 20797011

checkpoint_p0/milestones/checkpoint_000078592_80478208.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e21ee29a7a66fea4f45b31f23eaac85998d1b5a395a11f00b7866d1c930a18
+size 20797011

checkpoint_p0/milestones/checkpoint_000086432_88506368.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93f4e4960a932446ea149cf60ac7ea193f69c09b7376efd32d974c66643f52ff
+size 20797011

checkpoint_p0/milestones/checkpoint_000094304_96567296.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f1801658d682d37a7dc38bf2dddd31ec7c7c69392f63754bc0c39044b5c119d
+size 20797011

checkpoint_p1/best_000065376_66945024_reward_10.270.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2986eb405fa9d59baf732aaf12664c3fb38a31133b47eae7f04343692a1ac5cb
+size 20795763

checkpoint_p1/checkpoint_000097504_99844096.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d4b3ea871c9eb8e69c0ce3d52bc9d19e23cac56eaa9b86edbca4b4cedcb382
+size 20796099

checkpoint_p1/checkpoint_000097728_100073472.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d207a0916e129a4e4a151e6a34a5a2fb9a9f63a327ee4c8f0e78aab13a4607
+size 20796099

checkpoint_p1/milestones/checkpoint_000007776_7962624.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:258b89ae42352b25add12b90c368cc8b0ff39003175c6f6541ee1b5594eef186
+size 20796955

checkpoint_p1/milestones/checkpoint_000015648_16023552.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d768067a7a3f70c31782b02d8926cba7152c0cf71cef35866685101a572fbfb
+size 20797011

checkpoint_p1/milestones/checkpoint_000023488_24051712.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:823535e6fb84043479e757313597125703ed5089cd26c7833a79fe675901f25e
+size 20797011

checkpoint_p1/milestones/checkpoint_000031360_32112640.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1423fdc0fa6e93f80b501c376ac8e5169d90b38001ca750d2e258a24a2c9d5
+size 20797011

checkpoint_p1/milestones/checkpoint_000039232_40173568.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:221b6db2b4fb41d5e8abf95227790d3c4bfb0882238fb522b5e37315501f6497
+size 20797011

checkpoint_p1/milestones/checkpoint_000047104_48234496.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40648a71a56cbb69b5db45487bc2a0bfd9742cc0e1a32ecf8682b781e202832b
+size 20797011

checkpoint_p1/milestones/checkpoint_000054976_56295424.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5afbf0380545acbac260e052091839e374a893d4ecdc998ad2ca97bf5e6ade
+size 20797011

checkpoint_p1/milestones/checkpoint_000062848_64356352.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae37020765fc6ea42a0be0cb417e2aecbde57ba2699dcea6da4994f52cacabf2
+size 20797011

checkpoint_p1/milestones/checkpoint_000070720_72417280.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4fc24a432e05edc6cd8cf28a40afa1a4dd77fbecc91305112a7f80e4246c6b
+size 20797011

checkpoint_p1/milestones/checkpoint_000078592_80478208.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9813acf9941fa080abe6a2887d17aa05aa3a3cb94c2507bfada5eb0f36a35c1b
+size 20797011

checkpoint_p1/milestones/checkpoint_000086464_88539136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b57fe7c7ae1fee6bd17b5f9f352202714b02ccb719d5e0255d639703bf310543
+size 20797011

checkpoint_p1/milestones/checkpoint_000094336_96600064.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfcdd3be6c988b8ea46af4a4cb120f4403676d785d5c47118d20286185e1f23
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_kangaroo",
-  "experiment": "atari_kangaroo",
+  "experiment": "atari_kangaroo_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_kangaroo",
   "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_kangaroo --experiment=atari_kangaroo --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_kangaroo --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_kangaroo --experiment=atari_kangaroo_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_kangaroo --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_kangaroo",
-    "experiment": "atari_kangaroo",
+    "experiment": "atari_kangaroo_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_kangaroo",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_kangaroo_20230926_132233_743221"
+  "wandb_unique_id": "atari_kangaroo_APPO_20231012_154415_020036"
 }

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:fdb69cf3f15cb7e46862f317588ec2371a5a387a2c73285e5f5a9bee7890d18b
-size 1000638
+oid sha256:80476da5267416a1f3dae2a8e1d8c2c4fdc647364b81146ed17269ba5d9d2887
+size 6870486