Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697047556.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526e7d8807e0219d1b49155395ad9feb12d4e6163ab083eea3d67f3fefa53bdc
+size 7532714

.summary/1/events.out.tfevents.1697047556.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3949ff8ee5ac0c257414fbc0056c40dc6bb1f254b0fc3b5c77c07223df1e9d3
+size 4352587

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_gopher
     metrics:
     - type: mean_reward
-      value: 852.00 +/- 418.78
+      value: 10948.00 +/- 4990.36
       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_gopher
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_gopher
 ```
 
     
+## 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_gopher --train_dir=./train_dir --experiment=appo-atari_gopher
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_gopher --train_dir=./train_dir --experiment=APPO-atari_gopher
 ```
 
 
@@ -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_gopher --train_dir=./train_dir --experiment=appo-atari_gopher --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_gopher --train_dir=./train_dir --experiment=APPO-atari_gopher --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_000042880_43909120_reward_337.550.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af8b943dc33f576142f5ac1acc80ff9e4e5f1c9ec27b7040bd03b3a2d21bb6e
+size 20734131

checkpoint_p0/checkpoint_000097024_99352576.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a10642d61b3bf2476553326d379e8b84b45df2f3a83e4c65d1c18d00a687e9
+size 20734467

checkpoint_p0/checkpoint_000097760_100106240.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57f9e177c2c34a92c37a93b570dce74c5c889e370954c0d3a2ac85f35b939bc
+size 20734467

checkpoint_p0/milestones/checkpoint_000008384_8585216.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f6077e7f8776ffbad03bf6f159a423bbd35059fefe0b5553ecdb7722967dae
+size 20735323

checkpoint_p0/milestones/checkpoint_000016896_17301504.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78550c67d4f7f2fcb1fc658422c37242de01dc3aac4619c27ff5c5b8f844f074
+size 20735379

checkpoint_p0/milestones/checkpoint_000025408_26017792.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0392e2cb33d8eba40d355dac9ec53cfe785b4decc29568858b728ea27e24b2fa
+size 20735379

checkpoint_p0/milestones/checkpoint_000033952_34766848.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2abe5310acce678147de29d4e9cddd1ad75e305f79140d0c51f1c5e8e418813d
+size 20735379

checkpoint_p0/milestones/checkpoint_000042464_43483136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7639df3ace365fae8c104cf18fe0db1c1d3408139102ab6f68ee8d8170bac72
+size 20735379

checkpoint_p0/milestones/checkpoint_000051008_52232192.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4d5719dd546085873d38385f3016668b539ac1cfb3a0c1dad1d7411b19c123
+size 20735379

checkpoint_p0/milestones/checkpoint_000059552_60981248.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8488e96a4a5d212f070cdeeaf14272259e9348627e1e8b87e3325ca29bbbd8e1
+size 20735379

checkpoint_p0/milestones/checkpoint_000068064_69697536.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4acc3a95f85e0fd9664eaa81d1805a3ebe127ec6d84e6b2b45e6595d5c912573
+size 20735379

checkpoint_p0/milestones/checkpoint_000076544_78381056.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0f192bf84cb61e198ec580b311a5983eace3649fff821eababe51ad6c10459
+size 20735379

checkpoint_p0/milestones/checkpoint_000085056_87097344.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f9701589667a3be3a821ac2928dcee018f326d5ee2bccdad81c60062710184
+size 20735379

checkpoint_p0/milestones/checkpoint_000093600_95846400.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0517e866e9ebec8972811b850a8eb1c4b554c5ab61a27ac1830609d61755e218
+size 20735379

checkpoint_p1/best_000037152_38043648_reward_191.360.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a89b5ff936cb22850298adc9096ff7cb6affb0343b897fa7aa1a80e4935583
+size 20734131

checkpoint_p1/checkpoint_000096928_99254272.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840e7c0804e2708051f3c26cf8c924f5393da86c0c9ace764a4397739c47c80d
+size 20734467

checkpoint_p1/checkpoint_000097696_100040704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ca39149e7aebdb231ea89e5e4a5cd5d9154e2f50aeb8223fd5c153c8a2f570
+size 20734467

checkpoint_p1/milestones/checkpoint_000008384_8585216.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539dea6c67e88d0372d7b19b49d2bd62ec4818774f0211c9cb7bb0249f3b7df0
+size 20735323

checkpoint_p1/milestones/checkpoint_000016864_17268736.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78406be5ff1ad9b53b9358b1940c50b1cd91726c76e664850bb673c2c033f358
+size 20735379

checkpoint_p1/milestones/checkpoint_000025376_25985024.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf62708b620c9636beb2b74cdb0d6cfe3ecbbee2968c3978f3d44f98ec477f6
+size 20735379

checkpoint_p1/milestones/checkpoint_000033920_34734080.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:573deac6d541c9b1929e8585037616802e0108e24dd191bd0d30053a83a92240
+size 20735379

checkpoint_p1/milestones/checkpoint_000042464_43483136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793a07dfd99fae9f9d045cd840c5fecfa40e90fcd9aa3ae254ec87468b5f2db0
+size 20735379

checkpoint_p1/milestones/checkpoint_000050976_52199424.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e473cd473fe9863c476537a12545a72ade0c336c01b00e63e53e82e4a6d07c99
+size 20735379

checkpoint_p1/milestones/checkpoint_000059488_60915712.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ee84e6da9ffebd78fc4923ab70aa939557aaeb2f8db7d1e43a0106030816ca
+size 20735379

checkpoint_p1/milestones/checkpoint_000068000_69632000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9f32e51d94f15c9553abbbd6de6bc1ceac0724d6cbb4c4fbfba403fcdb4272
+size 20735379

checkpoint_p1/milestones/checkpoint_000076480_78315520.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bafca6458b35719213cb3ad41885248457eaf84592fa0d6cc84759fe14e9fb4
+size 20735379

checkpoint_p1/milestones/checkpoint_000084992_87031808.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a57c49dbdc17fa4845c16596afe527f00b704032089be87d4a210f95f069aa43
+size 20735379

checkpoint_p1/milestones/checkpoint_000093504_95748096.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:691de5a7686b9ff9156511b2b1ee4a57ae08f4e7bb909ae67b4f3787cb5d9d17
+size 20735379

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_gopher",
-  "experiment": "atari_gopher",
+  "experiment": "atari_gopher_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_gopher",
   "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_gopher --experiment=atari_gopher --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_gopher --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_gopher --experiment=atari_gopher_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_gopher --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_gopher",
-    "experiment": "atari_gopher",
+    "experiment": "atari_gopher_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_gopher",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_gopher_20230926_084144_469451"
+  "wandb_unique_id": "atari_gopher_APPO_20231011_190553_386475"
 }

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 sha256:631793d0faff501e1338ba79e3eaf966e1b3d991afa5e6dfef7ac704e550540d
-size 1541803
+oid sha256:20a3e661302811bce95772257e7c26e3993f93ee940255ae50ec6d488e1f0949
+size 6061940