Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1696909001.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba209f56458f930827141f8b05561c066ded02adce31f4a02ca0a635da532cb9
+size 8159839

.summary/1/events.out.tfevents.1696909001.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e9b75a55a709bf43d71bdf471c9308def980294c68cffd1aa53301ca313512
+size 4714966

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_choppercommand
     metrics:
     - type: mean_reward
-      value: 3500.00 +/- 1734.36
+      value: 35570.00 +/- 17871.60
       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_choppercommand
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_choppercommand
 ```
 
     
+## 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_choppercommand --train_dir=./train_dir --experiment=appo-atari_choppercommand
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_choppercommand --train_dir=./train_dir --experiment=APPO-atari_choppercommand
 ```
 
 
@@ -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_choppercommand --train_dir=./train_dir --experiment=appo-atari_choppercommand --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_choppercommand --train_dir=./train_dir --experiment=APPO-atari_choppercommand --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_000084416_86441984_reward_26.420.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b633ad9fcc137310b304cdee34ba7c34d1f8876c2155d296bbafc3cd47fa478
+size 20795763

checkpoint_p0/checkpoint_000097504_99844096.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe2db2fd7361aa4acea350adb472e24bf4a5229702561b3a740186af13e10f10
+size 20796099

checkpoint_p0/checkpoint_000097760_100106240.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65c34594a0411f74d119c864d4bfc27b4909262655ef9c4f9a70bc9ed3ab9840
+size 20796099

checkpoint_p0/milestones/checkpoint_000007712_7897088.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb3e73043d767b5f99b75e2129616f8f04a76b175a9ccc9eb5067eceea8f024
+size 20796955

checkpoint_p0/milestones/checkpoint_000015616_15990784.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67980307be6f06d5b6018918b938748493f3e140f2ed9c85e2b58ecedc75dc6b
+size 20797011

checkpoint_p0/milestones/checkpoint_000023456_24018944.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab509b1a1c6b9ab627ff095700f5a7befbd8ef2c7793fd0535c058701496489
+size 20797011

checkpoint_p0/milestones/checkpoint_000031360_32112640.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a835887da3374c3f2028f7a65e004c080e8d1f415ac2e058da0335d00740fb11
+size 20797011

checkpoint_p0/milestones/checkpoint_000039200_40140800.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4859eec8d5b7208cc40f335c3a02a6b22a5063e6aa3307febbc96a09147828
+size 20797011

checkpoint_p0/milestones/checkpoint_000047104_48234496.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d502d72a16a57bbe52f00f093682fcec9d5553c184f62306d6597d0dc22b417
+size 20797011

checkpoint_p0/milestones/checkpoint_000054976_56295424.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a5a87488fbdce44bf20df399cf52bb2183e7624db1f9a2dd211d337c5b96b83
+size 20797011

checkpoint_p0/milestones/checkpoint_000062848_64356352.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cda68ad5e2949d4d9ce06861d7acd1e4d8e49e3c91ba60d8c21e10fa4e36852
+size 20797011

checkpoint_p0/milestones/checkpoint_000070720_72417280.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e9d8e37d5935afd5cb8ee98146fd52df0ce97d7ec8778686dff22afa28a426b
+size 20797011

checkpoint_p0/milestones/checkpoint_000078592_80478208.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1074f831503ffbb389d8f775ecf34d0cfc55ff93114b9e5d40a02c5346fce6
+size 20797011

checkpoint_p0/milestones/checkpoint_000086464_88539136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f9c5c174767d478bbc491cdb6fafc3db87fd1b5fd81976e185965e076eb823
+size 20797011

checkpoint_p0/milestones/checkpoint_000094336_96600064.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8676ad3d2de3b151a685924d8cb21556ea455c96940d20aff644193f23b319cb
+size 20797011

checkpoint_p1/best_000087040_89128960_reward_25.390.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5a3ea9648598970e04d1ddbf035322b993517afe7f83000938e4e4b58d483fd
+size 20795763

checkpoint_p1/checkpoint_000097408_99745792.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35cb8de5f5fac279e3419c0f63f76def7858bfa0c6e52fc851242b0d51c47d18
+size 20796099

checkpoint_p1/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0dc35e492cc41e1a0469be317d72f3813369e8b6df0a354eed65417462cfeec
+size 20796099

checkpoint_p1/milestones/checkpoint_000007712_7897088.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ac4bf3e0a1d1711d7af1d70b7ded66f8f927bb377df24ffb8064b5db0f7f22
+size 20796955

checkpoint_p1/milestones/checkpoint_000015584_15958016.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874a9ffe04bdf4e4bf933ff37d536638f460a02825a7d7f84cb8ed9828426e26
+size 20797011

checkpoint_p1/milestones/checkpoint_000023424_23986176.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09b55a3493bbde75de140aa085560221ed04083969a14714e2899a3a4d35860
+size 20797011

checkpoint_p1/milestones/checkpoint_000031296_32047104.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e18ed2dc248d61da7b270811e52145d67ec10b088386f7f8f80e7398d5f6d4
+size 20797011

checkpoint_p1/milestones/checkpoint_000039168_40108032.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e13f35df57a83f0f9823bd8c3d02202f659ac3f32af9f0980a7f40824061d51
+size 20797011

checkpoint_p1/milestones/checkpoint_000047040_48168960.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79559129083a2c3fa2d75725c886e1a8cc74611a782272c2d792d3aff68bc0d
+size 20797011

checkpoint_p1/milestones/checkpoint_000054912_56229888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a97d8fc9737d9d2152870fa3f25dd2748ba7b7d434d011ee28721acfcd44972
+size 20797011

checkpoint_p1/milestones/checkpoint_000062816_64323584.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b7e4804c8f4814ecbf250aef76daaf0d2c05db7e9220f9c3b19d5a058d3f59
+size 20797011

checkpoint_p1/milestones/checkpoint_000070624_72318976.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9efd36c49cc010611af0f805a41e41086c7765c501ad7e3f02b77a794e216901
+size 20797011

checkpoint_p1/milestones/checkpoint_000078528_80412672.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d32fa2f4493bea17e732a6aca2f59a96b33a7a1db6a487b5f9d59ffddcc8a5
+size 20797011

checkpoint_p1/milestones/checkpoint_000086400_88473600.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:486a060794edea3c8cd4b364ebfcf2e26d7337db35c3164c28a349bd78fb70ee
+size 20797011

checkpoint_p1/milestones/checkpoint_000094272_96534528.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a459874f83683c451df9a8719a03a6115183a68148c3ecd062efd2acba86bc53
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_choppercommand",
-  "experiment": "atari_choppercommand",
+  "experiment": "atari_choppercommand_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_choppercommand",
   "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_choppercommand --experiment=atari_choppercommand --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_choppercommand --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_choppercommand --experiment=atari_choppercommand_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_choppercommand --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_choppercommand",
-    "experiment": "atari_choppercommand",
+    "experiment": "atari_choppercommand_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_choppercommand",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_choppercommand_20230925_235837_277155"
+  "wandb_unique_id": "atari_choppercommand_APPO_20231010_043638_197646"
 }

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 sha256:007d3523a42af79197042951d95465cb812c575aabb880028d05015813237c58
-size 2097095
+oid sha256:8cdd2efad6d5aad1d8005a1daf061d981c6ab930eae56ad35a2927423eb72406
+size 5438673