Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1696850003.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15bbc6440beb58c912a18f326ad8f34f626a7509effb485fb0df9cfb362080a8
+size 7524729

.summary/1/events.out.tfevents.1696850003.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e64db3e80a13def93ba9d15a03193e594d76f443aede20d9685821caf12ed37
+size 4348897

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_bowling
     metrics:
     - type: mean_reward
-      value: 97.10 +/- 7.74
+      value: 46.40 +/- 5.28
       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_bowling
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_bowling
 ```
 
     
+## 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_bowling --train_dir=./train_dir --experiment=appo-atari_bowling
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_bowling --train_dir=./train_dir --experiment=APPO-atari_bowling
 ```
 
 
@@ -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_bowling --train_dir=./train_dir --experiment=appo-atari_bowling --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_bowling --train_dir=./train_dir --experiment=APPO-atari_bowling --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_000003488_3571712_reward_10.000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c6b5c52858e5e90774d5a443c8dd8db7965ecf2cab3f9c9093b4525708f704
+size 20721843

checkpoint_p0/checkpoint_000096864_99188736.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d946d635799c2b57ae22a26d4a67cfc8ec89a573f2927d9ce8227cedb764a02
+size 20722179

checkpoint_p0/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee0154c14cf8a653a7d93e1c5dfe588d698b8a65d5549f1db9472d5aaf08ad82
+size 20722179

checkpoint_p0/milestones/checkpoint_000008320_8519680.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:723e0b18dc1bc44c11fe49c0626f272d326aae92618a2b14b8dc3d015cdbe341
+size 20723035

checkpoint_p0/milestones/checkpoint_000016800_17203200.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3382249f65d2578c8b874fbfa36a94bf3e826cac32a6add875fecbc21ae9dde1
+size 20723091

checkpoint_p0/milestones/checkpoint_000025280_25886720.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:882ff54c0633c37bd9ad5ae5fb3e213ce5cff5478ce83c9fd0a706f6c07b5e66
+size 20723091

checkpoint_p0/milestones/checkpoint_000033792_34603008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1d3df45cf2893e060c1a788b43c40a7738c78d8982ba00672666171cbda1aa
+size 20723091

checkpoint_p0/milestones/checkpoint_000042304_43319296.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:914877f0663a2d21c2ad110f9b6246cb332e2bd62b371ae49d6d4d0f9d602a73
+size 20723091

checkpoint_p0/milestones/checkpoint_000050816_52035584.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ad477595705efd140070ba13496c8afe3a6ecffa5444908d5fede266c21fb7
+size 20723091

checkpoint_p0/milestones/checkpoint_000059360_60784640.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c41f7b1567c2ecb0a0a7e3370ab9e4c5663ca3a6af82cea729d6c1f887b3bc6
+size 20723091

checkpoint_p0/milestones/checkpoint_000067872_69500928.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14bfd9838036f1b2da989705daa9dcd1a70c860ced25ba8aee1a19eecf6b3b4d
+size 20723091

checkpoint_p0/milestones/checkpoint_000076416_78249984.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2016c47609cd2b788bb4c125afd6a134791576fcb938730aa9b3900e622cbe0
+size 20723091

checkpoint_p0/milestones/checkpoint_000084928_86966272.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fdb4d35b8cf0d3456c20e8caadb10917f368d3fe280183aa8b9b9a2658b4c69
+size 20723091

checkpoint_p0/milestones/checkpoint_000093472_95715328.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbcdaeabf520a76a3b6061f241d488564fafea4b8daf4082e47732fe1bf41540
+size 20723091

checkpoint_p1/best_000002112_2162688_reward_10.000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:903912659bbb60f4df9b724798b7f668e4461d8355ab196cd9c84023785ecd78
+size 20721843

checkpoint_p1/checkpoint_000097248_99581952.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb5a2d79410190167183988376968aeb497e1324e05d28674927ba8aec66935
+size 20722179

checkpoint_p1/checkpoint_000098048_100401152.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a1716beb779a9efea0e8f0d5952e9b9e60b53e8bd02447ff60fb560d6d7c3a2
+size 20722179

checkpoint_p1/milestones/checkpoint_000008352_8552448.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63750b67f39a10c0b44efb659157aaef13820847428c35f8f10ebb642601580e
+size 20723035

checkpoint_p1/milestones/checkpoint_000016864_17268736.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f176ebe3075ff9122a4255152ea73cca36a7f9aaa132854b8f1307f99f4ebe3a
+size 20723091

checkpoint_p1/milestones/checkpoint_000025408_26017792.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7febe1090240899df26ad3d1ca65282aaf11e1b398737b48a8f6f239079966
+size 20723091

checkpoint_p1/milestones/checkpoint_000033952_34766848.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:471099ae7be2438a14be44e08ded1adcd2dd5a944d130e1cebe1e30185919ec0
+size 20723091

checkpoint_p1/milestones/checkpoint_000042496_43515904.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc0ff91adf258665bdd4d7abcf706f50101949be582bc248b8c9a061df5e150
+size 20723091

checkpoint_p1/milestones/checkpoint_000051040_52264960.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5af3c5ec50ef7e91f3f6057d73e8321af4eda5ff94d01e8b49d9836a6ebfe83f
+size 20723091

checkpoint_p1/milestones/checkpoint_000059584_61014016.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1033f05059633d7871c468c3fba2d27b87ea1d530effa043dd44536363688e6
+size 20723091

checkpoint_p1/milestones/checkpoint_000068160_69795840.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a77e2fdf721ad57bc902b4d10b997088f9752613107ef398af050dc259df0aab
+size 20723091

checkpoint_p1/milestones/checkpoint_000076736_78577664.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d530cd97ca08c4755d01689cb642c008946c65c878e25cb3dc56eda2dd1bdbaf
+size 20723091

checkpoint_p1/milestones/checkpoint_000085280_87326720.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1441ba0022935e006fb5d7520210b99690a0713024f0420732d95d501b2b3788
+size 20723091

checkpoint_p1/milestones/checkpoint_000093824_96075776.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f72130f55113af491193d6532c0225af6fd27bb94c4fc5fc70d8023abcd4e5
+size 20723091

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_bowling",
-  "experiment": "atari_bowling",
+  "experiment": "atari_bowling_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_bowling",
   "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_bowling --experiment=atari_bowling --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_bowling --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_bowling --experiment=atari_bowling_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_bowling --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_bowling",
-    "experiment": "atari_bowling",
+    "experiment": "atari_bowling_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_bowling",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_bowling_20230925_201827_962652"
+  "wandb_unique_id": "atari_bowling_APPO_20231009_121320_509191"
 }

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 sha256:01f494cdb7c66763054d356ab1a905e6a99bbdd4de518dd474dd21ec6def7443
-size 1386063
+oid sha256:36bcd5c67c731b3a640581cd4f87dc3fdc35da3aab4bfc3064197ee816bdd44c
+size 1486697