Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697391761.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ce56d312460bc82d50e916d8ff278215f01676262d7f534e39350857bb4f51b
+size 7487189

.summary/1/events.out.tfevents.1697391761.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f319d0da2930c0bf966713485be83c926ba23a42ded78312779f6b5c24641435
+size 4338229

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_stargunner
     metrics:
     - type: mean_reward
-      value: 10140.00 +/- 4558.33
+      value: 71800.00 +/- 8432.32
       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_stargunner
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_stargunner
 ```
 
     
+## 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_stargunner --train_dir=./train_dir --experiment=appo-atari_stargunner
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_stargunner --train_dir=./train_dir --experiment=APPO-atari_stargunner
 ```
 
 
@@ -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_stargunner --train_dir=./train_dir --experiment=appo-atari_stargunner --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_stargunner --train_dir=./train_dir --experiment=APPO-atari_stargunner --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_000085632_87687168_reward_33.790.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44749e630755462660bb517cf7031edcde2629f0910ad5c3b6c1fa12304c36e9
+size 20795763

checkpoint_p0/checkpoint_000097696_100040704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82f2f61e46b69e6d9e491dd714ca07ce3560e7cc23c39aac4b08b5b73d0089f
+size 20796099

checkpoint_p0/checkpoint_000097728_100073472.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc49d423efbb6e8fe7b349642ecc101cf40ac4bfb018c498e36154effefa8bc
+size 20796099

checkpoint_p0/milestones/checkpoint_000008480_8683520.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e2c5f3dc7ac05dc848521065e039658ab8f9fbaac7ed4bc78672000d7a4e75
+size 20796955

checkpoint_p0/milestones/checkpoint_000017056_17465344.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e750a89f7924332f3edcb201cf33039df90162668844fbbd264ba4d9c1edb209
+size 20797011

checkpoint_p0/milestones/checkpoint_000025632_26247168.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c4ae6717ef95870e02f2cd7831c5c09c248cf1c6bd95ad02115a237c0bc4f9
+size 20797011

checkpoint_p0/milestones/checkpoint_000034176_34996224.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6c68d7fcef24164081b8d638c339ac862f8ae9efd40c93c77580459ea4c4b3
+size 20797011

checkpoint_p0/milestones/checkpoint_000042784_43810816.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:480e6c65fd50f6b33388b3fa316ad13b9da659b81976fdb36d5032d9947f4f37
+size 20797011

checkpoint_p0/milestones/checkpoint_000051392_52625408.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c6233cc3e6e67a8850e32888a4f1488df6d2daff4f34560ab3ec8157033a5a
+size 20797011

checkpoint_p0/milestones/checkpoint_000059968_61407232.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd20e839ad9d189195a1025016ee259c7bc7ff2adea26e16ea2e8761f27c963
+size 20797011

checkpoint_p0/milestones/checkpoint_000068512_70156288.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fc2bc62fd4b6541127ea538a24cc070939cda6c2cc76d32a12ec9dac5639c20
+size 20797011

checkpoint_p0/milestones/checkpoint_000077088_78938112.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1aad9ac4e09e726fc4993ff8fd9687c994c32dee9821339b53ca294b835a4f
+size 20797011

checkpoint_p0/milestones/checkpoint_000085664_87719936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2807bc8ebc8cbc7e1e2b62496457e47c8c3e71589dfd337aff0a8e143cdd7e5
+size 20797011

checkpoint_p0/milestones/checkpoint_000094272_96534528.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce003923ba306f1ec70937fab1cd246286d059e1166174522e81b2d7a22fdd8
+size 20797011

checkpoint_p1/best_000051840_53084160_reward_33.300.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011a40251b9d92234edba08413c4878ca0e87dadfe1a72a8194f0f5986b37e93
+size 20795763

checkpoint_p1/checkpoint_000097632_99975168.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ed322bd37ccd14be10687f1761bc816a51bce99a66a774e23c173ad77e1a2d
+size 20796099

checkpoint_p1/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c697b899236fa47c1ceb251233635e2f6816439d1540da4106b8b9599e0eba0e
+size 20796099

checkpoint_p1/milestones/checkpoint_000008512_8716288.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d59e9e1b454c460bd1cca3dfa433a5cfc37549177d3269fbe2d6e3a0730280aa
+size 20796955

checkpoint_p1/milestones/checkpoint_000017088_17498112.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9ead64dbf7bcb005b66f0899632478ccfcd333618298e407eccf8a10caa23b4
+size 20797011

checkpoint_p1/milestones/checkpoint_000025632_26247168.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b405012a2f72b54d715101b8b8c45c8a765ecf64b744dde93c2d79e27aeb4f2
+size 20797011

checkpoint_p1/milestones/checkpoint_000034176_34996224.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6938afcc239600d3790fdcbe378cead5be8ab07592365d5d01e8e88d22d72a
+size 20797011

checkpoint_p1/milestones/checkpoint_000042784_43810816.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd6c5f1006ad851fa412073933f658898b32e1bc9279b221322468f948cc18d
+size 20797011

checkpoint_p1/milestones/checkpoint_000051360_52592640.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9dd6f079144bfd364ee8e699d729af0050b3639161261b0345193b642ce86f1
+size 20797011

checkpoint_p1/milestones/checkpoint_000059936_61374464.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e68d702e46add7424d87a61743ee1d323cf6d2385eb9521186736e8ec3383c5
+size 20797011

checkpoint_p1/milestones/checkpoint_000068480_70123520.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23bb273efea538e180efa1c1babf2f847e05ffd44130ac5a3906ae0f3213dad
+size 20797011

checkpoint_p1/milestones/checkpoint_000077024_78872576.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5126eda5320fc854abe5d9afdd61b41dddd46d742016de927cd9cbf8866f15a9
+size 20797011

checkpoint_p1/milestones/checkpoint_000085632_87687168.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7b5f69ecf13cdb0dffc12b9cfa24862868991b4972898ccb0708f994c6dad5
+size 20797011

checkpoint_p1/milestones/checkpoint_000094208_96468992.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750304b1c6ea06bcd3f67a5204a4324f8a4b79016be6ca59fa8a1daceeb8fcc9
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_stargunner",
-  "experiment": "atari_stargunner",
+  "experiment": "atari_stargunner_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_stargunner",
   "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_stargunner --experiment=atari_stargunner --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_stargunner --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_stargunner --experiment=atari_stargunner_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_stargunner --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_stargunner",
-    "experiment": "atari_stargunner",
+    "experiment": "atari_stargunner_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_stargunner",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_stargunner_20230927_062055_529293"
+  "wandb_unique_id": "atari_stargunner_APPO_20231015_184237_952702"
 }

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 sha256:9191b82b971c9986b8227b9e633dba7edad29c9669b489c790820857db29705c
-size 3222643
+oid sha256:5117a1c809571f509b1d96a2dc5a50deeb8d20c683be9b9ae170ec41613a5e62
+size 10380096