Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697286163.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e5f41aa6a8fad8568b3afaa6666964e179722bb436ff016541d6b987d96bc32
+size 8182361

.summary/1/events.out.tfevents.1697286163.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c9e27580f978417e93aef980866b0fe0d00ce12f9e6490982c257d4d87a90a7
+size 4737184

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_riverraid
     metrics:
     - type: mean_reward
-      value: 4935.00 +/- 459.40
+      value: 8855.00 +/- 577.95
       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_riverraid
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_riverraid
 ```
 
     
+## 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_riverraid --train_dir=./train_dir --experiment=appo-atari_riverraid
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_riverraid --train_dir=./train_dir --experiment=APPO-atari_riverraid
 ```
 
 
@@ -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_riverraid --train_dir=./train_dir --experiment=appo-atari_riverraid --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_riverraid --train_dir=./train_dir --experiment=APPO-atari_riverraid --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_000094528_96796672_reward_32.870.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f23c50d47bf00f536968f83125fbd4f9a95386203dd934bbc34ea636ce0801da
+size 20795763

checkpoint_p0/checkpoint_000097312_99647488.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c8d5fd7d5be974f6e33578d5f38857174d5a9d157faaab247f4db4b8ce5571
+size 20796099

checkpoint_p0/checkpoint_000097952_100302848.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29065020c233736989020f1fa9b7371970031f474f742f0c333fe77c9740b849
+size 20796099

checkpoint_p0/milestones/checkpoint_000007712_7897088.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddfbfe29c02208369f0aca2d4552e89b8c45540665c53ff2b9dee52626edd6e3
+size 20796955

checkpoint_p0/milestones/checkpoint_000015552_15925248.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95fc903c54380d644a12347b21a63504272adcd3541b7b4490feb36db3fe7170
+size 20797011

checkpoint_p0/milestones/checkpoint_000023392_23953408.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c4c6f7806e0e85baebee0c32987d3ef53f807cffa8c504b55791cc1897a9e52
+size 20797011

checkpoint_p0/milestones/checkpoint_000031264_32014336.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65f6ab56174b7973dc736019831ec5505da0a4358cf2b3f6d1889a9c1359817
+size 20797011

checkpoint_p0/milestones/checkpoint_000039136_40075264.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b183540085295035f7e773179ce80171ca888720ce5ab190053465b88a40e34
+size 20797011

checkpoint_p0/milestones/checkpoint_000046976_48103424.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e1e9e934b3f777c28537beb308a1f33425e73e4457c18d6aef8b09cfca2bb8
+size 20797011

checkpoint_p0/milestones/checkpoint_000054816_56131584.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74fe8cf14f55c24a3765dfbc926f8ce07e5e1ffc1e15b3485fa4513eb78ac2b
+size 20797011

checkpoint_p0/milestones/checkpoint_000062688_64192512.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b6b48810f6db400d23ecb3352d196fd7454aeddb0a5c438c6595a27b947d33
+size 20797011

checkpoint_p0/milestones/checkpoint_000070560_72253440.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb4c251abe8f2882fa306ddacde1cc01ca47a6f585ee6acc8d77334e714fe8b
+size 20797011

checkpoint_p0/milestones/checkpoint_000078432_80314368.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f0557ad0d265e9ba8b5498f7c724b00910ba9632c84326a7d7a3f8c98e009b
+size 20797011

checkpoint_p0/milestones/checkpoint_000086304_88375296.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549ea7a88be8730f96d9138ea263ed04c9cfcc206ac75e1b1878b31d4ce95a47
+size 20797011

checkpoint_p0/milestones/checkpoint_000094176_96436224.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1714ab52dcad29d3611e6ef6f82e26a33816715364c97f4bf876fcf87e636e6
+size 20797011

checkpoint_p1/best_000092896_95125504_reward_39.930.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c7e5dd78989abf4da9f4e5fb24596939f19ad253ee997a89973be54d1e6e2f
+size 20795763

checkpoint_p1/checkpoint_000097056_99385344.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838841df3055fa4ec929ac01fba0a54cadd3beef766b612d98cbf1a6ef7dbabd
+size 20796099

checkpoint_p1/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab9186fb09f3c88dd7a343aaadba28469ce979ea47eb8f325d31b2f1eb876ec
+size 20796099

checkpoint_p1/milestones/checkpoint_000007712_7897088.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d3e583a40f7acb301d2ea6d0f3a4648e88a6392d198419df798661ee156430
+size 20796955

checkpoint_p1/milestones/checkpoint_000015552_15925248.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e69b1189c786b7bff8d5b2d8122fd8bf675036f80dcce1c61861e1e388ab59c
+size 20797011

checkpoint_p1/milestones/checkpoint_000023360_23920640.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:985533972a5c0bcab2ec4a862a2c782b4ab42fc3524ef0580043fc841957455d
+size 20797011

checkpoint_p1/milestones/checkpoint_000031200_31948800.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9380ee4e636470e7c387f44dc80e0a98c4980b100111bd2c3c90b1277e4f4301
+size 20797011

checkpoint_p1/milestones/checkpoint_000039040_39976960.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89fd96fbd34279006d899af68e7fa90bfc0aeab2815d3a02f4a920550584fd88
+size 20797011

checkpoint_p1/milestones/checkpoint_000046880_48005120.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c6177e9762dfc655d3959baf66c46f25cc7618da36c4d4c27fa95d6c14d8e16
+size 20797011

checkpoint_p1/milestones/checkpoint_000054688_56000512.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0201003a9ae7e9d26455ef7e4ec3601478684e8e6e85bbe9a0ac899be9eadcf1
+size 20797011

checkpoint_p1/milestones/checkpoint_000062528_64028672.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e46fb17ddcbd4182fe1a5bc0deb5aae658fd69043ae672596ae933841300d0dc
+size 20797011

checkpoint_p1/milestones/checkpoint_000070368_72056832.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6befe40a0d1a48cf9186ea108b0c4a6d019399b22cf4face37c828d1f161c2f
+size 20797011

checkpoint_p1/milestones/checkpoint_000078208_80084992.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7678273e41abe32eb1be0dbcd4da0dc809f6d7e2261ab885c215d3666475635c
+size 20797011

checkpoint_p1/milestones/checkpoint_000086048_88113152.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ebcdb8cb87e1f203234880732040652dad9965c83428806120c4f1fd37a5ee1
+size 20797011

checkpoint_p1/milestones/checkpoint_000093888_96141312.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb85b8face8d602c3d560c6cfa177d40c1e5d69343cf38f62515cfde0c13cfc
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_riverraid",
-  "experiment": "atari_riverraid",
+  "experiment": "atari_riverraid_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_riverraid",
   "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_riverraid --experiment=atari_riverraid --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_riverraid --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_riverraid --experiment=atari_riverraid_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_riverraid --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_riverraid",
-    "experiment": "atari_riverraid",
+    "experiment": "atari_riverraid_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_riverraid",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_riverraid_20230926_234335_268516"
+  "wandb_unique_id": "atari_riverraid_APPO_20231014_132240_388669"
 }

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 sha256:4e736bd48d3af8d74df04136a6b923f4097f789f922d117f67057a4b5d57c2b1
-size 2875600
+oid sha256:65401be6a06fe8952a9d5417b17751be9f8879860beb4ca1bdff96da4f0ac9b6
+size 3294333