Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697226776.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f107107de1468617266b3c94a8400c3c3564cd6da50b1cc5d398050fe4185a
+size 8113991

.summary/1/events.out.tfevents.1697226776.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa0fcf2aaf448a04f5151ef20edf1b571179bd37456b3b9977089c06303fa7c
+size 4684420

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_pitfall
     metrics:
     - type: mean_reward
-      value: -43.90 +/- 67.24
+      value: 0.00 +/- 0.00
       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_pitfall
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_pitfall
 ```
 
     
+## 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_pitfall --train_dir=./train_dir --experiment=appo-atari_pitfall
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_pitfall --train_dir=./train_dir --experiment=APPO-atari_pitfall
 ```
 
 
@@ -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_pitfall --train_dir=./train_dir --experiment=appo-atari_pitfall --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_pitfall --train_dir=./train_dir --experiment=APPO-atari_pitfall --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_000001088_1114112_reward_0.000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ac5e1f95d8914404f80ba6dc8c72fc7aa7ead9e08ccf17879e689664768a85
+size 20795763

checkpoint_p0/checkpoint_000097184_99516416.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655fff0f052a5751fa0c6045a9237d4abcc50f44eb4695a98422992a46c8ae09
+size 20796099

checkpoint_p0/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e19874c2688aabaf375213f918e26861c9f396d0476e65aeb975087aec3b60
+size 20796099

checkpoint_p0/milestones/checkpoint_000007680_7864320.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b353c0332a5e3ef5a3a55e4694537736a61004a9e9e544c31b7b179c10e104
+size 20796955

checkpoint_p0/milestones/checkpoint_000015520_15892480.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7462ec1f75ff3065ce947aabb9fd8c607fa3a7d9cd910a61e865562f43404c88
+size 20797011

checkpoint_p0/milestones/checkpoint_000023296_23855104.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001cc869cfa90c7a0c64d62eb4cb791f62729fb8b23c48a2931d75f1a95f4194
+size 20797011

checkpoint_p0/milestones/checkpoint_000031136_31883264.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907d6c8bc298889830116ef9abc06e199b735f7cf87b76ecbc0142d8a4fbcdc8
+size 20797011

checkpoint_p0/milestones/checkpoint_000039040_39976960.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597c1370ae56fca805f587384e45a713eb3f9e4e054e258daf21dae6068372dc
+size 20797011

checkpoint_p0/milestones/checkpoint_000046912_48037888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02358d86e0cdfcf48fb0cd3406ad02f41ad8369f5cbe6a0886daf41de014c525
+size 20797011

checkpoint_p0/milestones/checkpoint_000054848_56164352.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67960f81a32f739e19da022b998265a2b8550ef76f18d88df08de134c130d499
+size 20797011

checkpoint_p0/milestones/checkpoint_000062816_64323584.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:656ea8a95bd1eecfc3d46753fca08566eed1a22e517b2cbe8335a4cd251fdf33
+size 20797011

checkpoint_p0/milestones/checkpoint_000070816_72515584.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af88cc782e99e3952f77464f2112c5c6f9536d77e6955a0e73096855e94ac4d
+size 20797011

checkpoint_p0/milestones/checkpoint_000078848_80740352.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc1b85f9e49918d10c8e1ae204b1c85e4df1312c6b9f283b81c11b38cdb676f
+size 20797011

checkpoint_p0/milestones/checkpoint_000086848_88932352.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0e171992c874156ac43d2807766dcb6a2d2a536e83a73936d48c2c11bdc526
+size 20797011

checkpoint_p0/milestones/checkpoint_000094784_97058816.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee16e10b190b8e9540e5ee9322f90199193c13aedff5e7a52fd95fb1fad2fd91
+size 20797011

checkpoint_p1/best_000000864_884736_reward_0.000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664a5033a3e0d5cbcae5661bdbe602fa926cec34e980762788526bc91b25d31b
+size 20795763

checkpoint_p1/checkpoint_000095992_100368384.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa9eeea1d6cb9b673b3cdc832547cfe37d131350b6cf9e4289be0190323262d1
+size 20796099

checkpoint_p1/checkpoint_000096504_100892672.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e5ba5f0705fe0a4f59f6e095c60bc9ef4d941c191ed65cfe439bfedf53874e
+size 20796099

checkpoint_p1/milestones/checkpoint_000007712_7897088.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b30ba1e104f7144254098bdad898c29f70b5297aa37d6532802285d7f12b9b
+size 20796955

checkpoint_p1/milestones/checkpoint_000015648_16023552.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:548fb35a0a73361571f86b10feb68a36a677ee93060db435dd69dc9ea80960b6
+size 20797011

checkpoint_p1/milestones/checkpoint_000023552_24117248.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37ecce0374401c749454eca205049103c72fb1042ebf0481d209a9e8481c020
+size 20797011

checkpoint_p1/milestones/checkpoint_000031520_32276480.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c1ea0afccb6ca5be5a7dcfa9e70275537422c0afda4008242a2db8f921d809e
+size 20797011

checkpoint_p1/milestones/checkpoint_000039472_40468480.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30918e9ace201010fa57e374cceb9d62e48dce1e348f9ab2bd3485f01fe9682b
+size 20797011

checkpoint_p1/milestones/checkpoint_000047256_48693248.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf6709ebc1e5c8f368211a16a7d360bfb0057a268a6ea2444edb63326023e67
+size 20797011

checkpoint_p1/milestones/checkpoint_000055256_56885248.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0206ea97a1d1a5b271d97687b55973e2c09910db59d94a7b1bbef097174c89e2
+size 20797011

checkpoint_p1/milestones/checkpoint_000063192_65011712.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:095e680ca6c80b83a78e63f6c176db044d8105bdc1c25b084beab7cbce5173c6
+size 20797011

checkpoint_p1/milestones/checkpoint_000071096_73105408.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3639835ee321914d88036e4ac406f66dc49110d78f6e83eecef2f7eb9811a64b
+size 20797011

checkpoint_p1/milestones/checkpoint_000078632_81330176.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d34a174682a6ab3ef7ecd5f1690808784f5e0fde8e8e1d2fb0f8ae6e9ca80a38
+size 20797011

checkpoint_p1/milestones/checkpoint_000086384_89587712.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2e016d16eb52c48d1d15e9e539cb6ddc07cbef84e4194a1eb872bd0e41e487
+size 20797011

checkpoint_p1/milestones/checkpoint_000093592_97910784.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:178f72c78e39228d74860ab8d18555a1152b92f2f88239c291e705cebee8706f
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_pitfall",
-  "experiment": "atari_pitfall",
+  "experiment": "atari_pitfall_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_pitfall",
   "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_pitfall --experiment=atari_pitfall --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_pitfall --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_pitfall --experiment=atari_pitfall_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_pitfall --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_pitfall",
-    "experiment": "atari_pitfall",
+    "experiment": "atari_pitfall_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_pitfall",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_pitfall_20230926_195458_856793"
+  "wandb_unique_id": "atari_pitfall_APPO_20231013_205253_019423"
 }

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 sha256:4123acb85708fce8e661e159d7e4e6e5acc91bc7c866e2a22279995c48bc7482
-size 16619310
+oid sha256:6b1b432f6c42980aa9a3ad36739f48a853ef241ca2d9ed08391afc12fa42e097
+size 1140918