Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697271245.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc363c93abfe550fb2658f3fef4d5677309ca88c9bc304c3fa7fc3e115f3bf7f
+size 7921698

.summary/1/events.out.tfevents.1697271245.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e5b5e63f5a510d30dec7d734d2caf7b94a67fcd01e726517c68b7571c6ed24b
+size 4584567

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_qbert
     metrics:
     - type: mean_reward
-      value: 10610.00 +/- 1446.77
+      value: 30000.00 +/- 2753.45
       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_qbert
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_qbert
 ```
 
     
+## 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_qbert --train_dir=./train_dir --experiment=appo-atari_qbert
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_qbert --train_dir=./train_dir --experiment=APPO-atari_qbert
 ```
 
 
@@ -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_qbert --train_dir=./train_dir --experiment=appo-atari_qbert --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_qbert --train_dir=./train_dir --experiment=APPO-atari_qbert --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_000097760_100106240_reward_112.440.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dac5d63c23dbce00a0bd6ac325ec7d1c39d4c65eb0234a2e804a808d48da1ea
+size 20721843

checkpoint_p0/checkpoint_000097760_100106240.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed7f4ea6bd6fd58b5c1d260dde7746cca7c94c55c85cb1459c1234a6a2323cd
+size 20722179

checkpoint_p0/checkpoint_000098240_100597760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c548b8ab6266555f13ef5562e696c724ebd08539e189a88c57cf53f77f7c48
+size 20722179

checkpoint_p0/milestones/checkpoint_000008000_8192000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52602ab7a74b50db3d7e06cc23a12847fd4f054961c9bc05dfe1081ec015fc2a
+size 20723035

checkpoint_p0/milestones/checkpoint_000016160_16547840.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f022a4d9f3a3ef08cfe0f12ac6515628dd5e072c67f6bfa785f901171142f3e
+size 20723091

checkpoint_p0/milestones/checkpoint_000024320_24903680.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0d8c293f36bf0e9732f2dd819726de0090055b7af6dc317af017e327bed8d0a
+size 20723091

checkpoint_p0/milestones/checkpoint_000032448_33226752.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19834931bda02a326fba0c443c17e9950838a69b7c844fe64bd3d4b98e1c1272
+size 20723091

checkpoint_p0/milestones/checkpoint_000040608_41582592.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fdd0303b28d6b4c8eb40b23ec864925a9beac9aa78cfbb0ddafeeb6d19f5e59
+size 20723091

checkpoint_p0/milestones/checkpoint_000048768_49938432.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b7eeba2f8442f90be2dd64ba1c080120ae20cea04b57957b280bd4a7f47bc3
+size 20723091

checkpoint_p0/milestones/checkpoint_000056896_58261504.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23cb1c712e7decef9cb7022e9aa38aac9339765ef0842e379222ef03107d3b0f
+size 20723091

checkpoint_p0/milestones/checkpoint_000065088_66650112.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feca2a1f2adde08ec2aa380f5c9c592f26a633efc00345d0303a1cc7f1204eb4
+size 20723091

checkpoint_p0/milestones/checkpoint_000073248_75005952.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f404ccd31cc22085913875b2943ab08141653082a68eb9994bf79416a61cfb5d
+size 20723091

checkpoint_p0/milestones/checkpoint_000081440_83394560.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86bd6562aaeeb3b8c41e4ad2989df87ad952151ebe511745f5d74442b33d49f3
+size 20723091

checkpoint_p0/milestones/checkpoint_000089600_91750400.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6546b54e5ce90b0061748597d5a37513b0f1dc3e2a586fb35ecdb46a1e42db44
+size 20723091

checkpoint_p0/milestones/checkpoint_000097760_100106240.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e5b88f74ed6b42b84e931a72a58e0df7bb3d2a8b6a8cb3cc700318688126491
+size 20723147

checkpoint_p1/best_000092192_94404608_reward_101.290.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1db85f101b9302535070fea039f9dc87aaf7b1701cf629bb7ce6bb40a867ed
+size 20721843

checkpoint_p1/checkpoint_000097216_99549184.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d6957171181f137345d535e9066e16b7a6bf4895ccc4f3f1b6b2385565df41c
+size 20722179

checkpoint_p1/checkpoint_000097696_100040704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af2ec03974ebe326d7b7490477eba5451ecadb1e55adc23035f9a48453ef1be
+size 20722179

checkpoint_p1/milestones/checkpoint_000007936_8126464.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e47e9396f91be93083e800e3be2e3bee341f6eb7f66c1584234f2f3f1c16329
+size 20723035

checkpoint_p1/milestones/checkpoint_000016064_16449536.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe37fbd1c7782abc0d294bd26b3abd72dbecf9a8b06775b14c09cde56396759
+size 20723091

checkpoint_p1/milestones/checkpoint_000024160_24739840.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:512017521895311d60663d38b24397affc816135c735599f6d3b57d95b2349e4
+size 20723091

checkpoint_p1/milestones/checkpoint_000032256_33030144.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870ac110bedcb93e00586d96951f85882161cdd1bc48a4b2c400ae0efb2f4c61
+size 20723091

checkpoint_p1/milestones/checkpoint_000040384_41353216.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d159df032766ecaf2bf40c772eb6f68e10a6eca8e6d7f5ee258c5dade5a1a519
+size 20723091

checkpoint_p1/milestones/checkpoint_000048480_49643520.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b377e3870c1c469c141e113da96aa01401ac87715542d9d520be1458825f6fc
+size 20723091

checkpoint_p1/milestones/checkpoint_000056608_57966592.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb92c875259d6b9648def8608da5f16f97f852524f8cb2f271a106136048c97
+size 20723091

checkpoint_p1/milestones/checkpoint_000064736_66289664.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a66d4120ba8331b3e439456b1846be30577e07783f6d87f334699f054caf02
+size 20723091

checkpoint_p1/milestones/checkpoint_000072832_74579968.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92fa1777f442e321b33f49f384e908ccb296213fb4ffd67911dc9fde798d31c
+size 20723091

checkpoint_p1/milestones/checkpoint_000080960_82903040.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9354edd564f5f3691c429a279b838822f10d2ab3c14d096879da14733d17fd02
+size 20723091

checkpoint_p1/milestones/checkpoint_000089120_91258880.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da27439869270a9f551ff5dafb66f253f0db5fda4ab3a3a43b778b086e63478b
+size 20723091

checkpoint_p1/milestones/checkpoint_000097216_99549184.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ee0c84130fac28d5b6acf0bdc083d4d4ff88ce6e0a7c9811a0ae12baff91a6
+size 20723091

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_qbert",
-  "experiment": "atari_qbert",
+  "experiment": "atari_qbert_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_qbert",
   "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_qbert --experiment=atari_qbert --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_qbert --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_qbert --experiment=atari_qbert_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_qbert --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_qbert",
-    "experiment": "atari_qbert",
+    "experiment": "atari_qbert_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_qbert",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_qbert_20230926_224933_963868"
+  "wandb_unique_id": "atari_qbert_APPO_20231014_091403_046593"
 }

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:a3c6133616bbcc7efb04fd36f7aa8e68f03d90e405fa76e05edc26b0ea87e003
-size 3090995
+oid sha256:9655972bd97b6029687c6e3120f7f00bd66410e956b0c33db3332415155c708e
+size 9874485