Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697301223.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ea2a77a745f2a435869e0fb38826fd4180ef012beb6170edb16df37ae6ceb5
+size 8211089

.summary/1/events.out.tfevents.1697301223.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a81505db2a5812e242378ec8537f7d0b0e9cde71772206fc80f0a5b53af7928
+size 4757632

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_roadrunner
     metrics:
     - type: mean_reward
-      value: 31770.00 +/- 4629.48
+      value: 65540.00 +/- 7998.52
       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_roadrunner
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_roadrunner
 ```
 
     
+## 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_roadrunner --train_dir=./train_dir --experiment=appo-atari_roadrunner
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_roadrunner --train_dir=./train_dir --experiment=APPO-atari_roadrunner
 ```
 
 
@@ -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_roadrunner --train_dir=./train_dir --experiment=appo-atari_roadrunner --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_roadrunner --train_dir=./train_dir --experiment=APPO-atari_roadrunner --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_000083168_85164032_reward_88.540.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda958861b788c34548f85f832ee4a1a8957e62f3443835decc272ef36678f48
+size 20795763

checkpoint_p0/checkpoint_000097696_100040704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:804cade57dc964b34593b90389660556aa77dd1c2002381a45acbac724642437
+size 20796099

checkpoint_p0/checkpoint_000097824_100171776.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bcac4624a17a7e5caaebbfc0396afae64342f33abf70b8e1c060891d5539ad1
+size 20796099

checkpoint_p0/milestones/checkpoint_000007648_7831552.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8a37610869aea0df0f15022dc7cb3561c695e1a3d11932a6cd9aa142ec6e0e5
+size 20796955

checkpoint_p0/milestones/checkpoint_000015488_15859712.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b81df503ba26c793d8ca1c72e3099d10328deddb109459704726284cbb75a69
+size 20797011

checkpoint_p0/milestones/checkpoint_000023296_23855104.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82ebfe12d443fad874326b667d207425bc666bb560f6ec37af9c6d7a4a37b8bc
+size 20797011

checkpoint_p0/milestones/checkpoint_000031136_31883264.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e269b210102a4417b9f5a4e86ac324d707bcbfe8263b603759496a406067ad5f
+size 20797011

checkpoint_p0/milestones/checkpoint_000038944_39878656.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99bd52870feaf5ede1d73d1e89dade88978ef7ccef37c07ec141b5fb4e83046b
+size 20797011

checkpoint_p0/milestones/checkpoint_000046784_47906816.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8c8ce5d32037b03b1f24b7e86b02a7b7b59c7ecc5fbd25170d36a47bfb1154f
+size 20797011

checkpoint_p0/milestones/checkpoint_000054624_55934976.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b97c778a8727f4413c8a7fe3887f4d3a3238e77e7aaf45c1b03f74ea26867d
+size 20797011

checkpoint_p0/milestones/checkpoint_000062464_63963136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:446d4fc67fb2b098cacd9e26902fd7c9cdbf4e99d4deec1cb9e4fbc42240cbe8
+size 20797011

checkpoint_p0/milestones/checkpoint_000070272_71958528.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbcb5a3c7501488978207dd428949750bb862b10427e20e4e7869aff41db6816
+size 20797011

checkpoint_p0/milestones/checkpoint_000078080_79953920.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e0230a37e20ddbd9ac13f601a18b82a272ac4db7038d498fef99c59a6ef741
+size 20797011

checkpoint_p0/milestones/checkpoint_000085920_87982080.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8602d12c2fc83e7c08bc3191050de0358255f1cdbbb7793c7d3d4cba30211d0f
+size 20797011

checkpoint_p0/milestones/checkpoint_000093760_96010240.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd685a05e3bea16aa41f4c72b273447767ea2fedad65f612e8d0569d00759969
+size 20797011

checkpoint_p1/best_000096320_98631680_reward_87.760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96aac82c88c3a5d0c479daf18ed544f2042f11953f3f4e1b2cb583670f598e4
+size 20795763

checkpoint_p1/checkpoint_000097536_99876864.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:122d4cea09d65a0bf37d5e7d4cf51b39f70bb07f47ca1799c1e8fab48b80696e
+size 20796099

checkpoint_p1/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ef08c537f27b7b614230f1312bb6182f1f6c27746565abaa8aad3021f6cc4c
+size 20796099

checkpoint_p1/milestones/checkpoint_000007648_7831552.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a140e69f95ea59922342973097f673f940d71d70376915727795f7ab513af8
+size 20796955

checkpoint_p1/milestones/checkpoint_000015424_15794176.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68743a3f0ed48a78337c46940601083bce05f7e5ed84e72a44c8c9ba9d6eafd0
+size 20797011

checkpoint_p1/milestones/checkpoint_000023232_23789568.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fbac07ce281d229fc736472d0bb2f430c752563af643c3693f9d49479aedc44
+size 20797011

checkpoint_p1/milestones/checkpoint_000031008_31752192.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa81e622bbc778b9dc29d5a086833b29a890a76b65bf342a5a46a375c3811a8a
+size 20797011

checkpoint_p1/milestones/checkpoint_000038784_39714816.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0189706ec91fdd029617a45b7e2bb5fb43cf57230a1464c89f9ec3b59c13d334
+size 20797011

checkpoint_p1/milestones/checkpoint_000046624_47742976.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab3024afbac636d0e87f178fa2875d88756420c90e688031ca5d9253a565f59
+size 20797011

checkpoint_p1/milestones/checkpoint_000054464_55771136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db4c3d186a1969d147b692531be0365c74cb51489c3d3ccc0d24e5550cbdc50e
+size 20797011

checkpoint_p1/milestones/checkpoint_000062304_63799296.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d1272fac7a7b059140bb29f6206041fd8093c3273ea6137ab227a9905f3844
+size 20797011

checkpoint_p1/milestones/checkpoint_000070112_71794688.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:100b2c198b38c41ba371446da6b759d96312733fca3a9d3347295b32d789159d
+size 20797011

checkpoint_p1/milestones/checkpoint_000077952_79822848.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af4f1de0380531f520bcbf2ec7e4baeb76405caaf4ed9c60dd52cecac35dc74
+size 20797011

checkpoint_p1/milestones/checkpoint_000085792_87851008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44863b37bf03ff156cbe7809a22909a2b38b47b62d2ee50969f0f2bd7a7e8441
+size 20797011

checkpoint_p1/milestones/checkpoint_000093632_95879168.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3865ff61f6bd325aad48a314cb1d0d64527c77150cd6934cfbc01533aecc119f
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_roadrunner",
-  "experiment": "atari_roadrunner",
+  "experiment": "atari_roadrunner_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_roadrunner",
   "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_roadrunner --experiment=atari_roadrunner --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_roadrunner --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_roadrunner --experiment=atari_roadrunner_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_roadrunner --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_roadrunner",
-    "experiment": "atari_roadrunner",
+    "experiment": "atari_roadrunner_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_roadrunner",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_roadrunner_20230927_003809_480134"
+  "wandb_unique_id": "atari_roadrunner_APPO_20231014_173340_754214"
 }

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 sha256:8cb3828048e6bd1faf8c646edc04ffc828b03521d5da265240e7fad956140d0c
-size 2951085
+oid sha256:cb735448a6ce01435a0ef3e5d6a16a95d24b0e6c825488bbc1c8494ae58e6171
+size 4689648