Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1697152313.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e7fe23c3d3ac3d82666f9be0abe4978b705860d486e9e6c5ee9f50d59a1ca2
+size 8171231

.summary/1/events.out.tfevents.1697152313.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de523e2d7d0b7d0643340ce38144a5db79ba17fb231ea7b370eaf8b880fe36f1
+size 4724758

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_kongfumaster
     metrics:
     - type: mean_reward
-      value: 18540.00 +/- 5298.34
+      value: 47520.00 +/- 10708.86
       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_kongfumaster
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_kongfumaster
 ```
 
     
+## 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_kongfumaster --train_dir=./train_dir --experiment=appo-atari_kongfumaster
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_kongfumaster --train_dir=./train_dir --experiment=APPO-atari_kongfumaster
 ```
 
 
@@ -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_kongfumaster --train_dir=./train_dir --experiment=appo-atari_kongfumaster --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_kongfumaster --train_dir=./train_dir --experiment=APPO-atari_kongfumaster --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_000078784_80674816_reward_68.210.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c8fd4bbec8152f83ede5587d4a75fdb6fcd636c976b53ed48e009bc7121ebe
+size 20770995

checkpoint_p0/checkpoint_000097312_99647488.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e693bccca2e5e664a636de828bdd2750610020740b487c0815bd5045d313a933
+size 20771459

checkpoint_p0/checkpoint_000097760_100106240.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88504a3278449c5d85595ffc6ba167fd2cfe08af53121a290cca520ffe5fec43
+size 20771459

checkpoint_p0/milestones/checkpoint_000007712_7897088.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59854935eef61bc5b20cbd17d1ecdeadb7e2635c3d60b12132992a2b752e4a3c
+size 20772379

checkpoint_p0/milestones/checkpoint_000015584_15958016.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d254c597817cf9e607c0ff3d10ff29359194c03d0bc8b62cb365c11a3d1375dd
+size 20772435

checkpoint_p0/milestones/checkpoint_000023456_24018944.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf12bd6621260fe8fb897b44a28be493ed923601b00f4fd2da8805560b91139
+size 20772435

checkpoint_p0/milestones/checkpoint_000031296_32047104.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ab9489f814ba1edb94315ce678e6e10c2f45fd3adf1351c07c52ada72e8e97
+size 20772435

checkpoint_p0/milestones/checkpoint_000039168_40108032.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad54071465c07cb79220d5c69bccafedb1c6b1c6744cdfb0a87d2c3179b8004
+size 20772435

checkpoint_p0/milestones/checkpoint_000047008_48136192.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce48519720ac37f22a336f6568094d3a7286f20fbf9b77e14de7ab4446e0caf7
+size 20772435

checkpoint_p0/milestones/checkpoint_000054880_56197120.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30215321642d15488bab3d8a52ee401485370855fd7f76db9b99ce69e3f506bd
+size 20772435

checkpoint_p0/milestones/checkpoint_000062720_64225280.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a00e11d8a26b4642489e2223a86f411c9167d716b2b462ebc82213b3cf5e714
+size 20772435

checkpoint_p0/milestones/checkpoint_000070592_72286208.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abfec62145852401aff5a8034276ae0daabc81e6414a6f4a94e2cdf79d941461
+size 20772435

checkpoint_p0/milestones/checkpoint_000078464_80347136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6f92b0cbb8067dbc5346eca7315036bb0d8604c1c88a3b2a8a4274235b7ea9
+size 20772435

checkpoint_p0/milestones/checkpoint_000086336_88408064.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0fbc82f04ac6079d36a499587f354c87b7b66659bb5f5b0df449252ae5d2e56
+size 20772435

checkpoint_p0/milestones/checkpoint_000094176_96436224.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7042c48b1897043980d5ad982ed1470af6f01bc894256ef7b04379b275566d7a
+size 20772435

checkpoint_p1/best_000097280_99614720_reward_63.360.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e90c774d0780f357c9952d05959331a5ab40ccacb5f5ef68366043726f2307d
+size 20770995

checkpoint_p1/checkpoint_000097216_99549184.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1110d3ee495f378415cc2d698002bb3e60a06d8d013ac2e742d96755ddf7164
+size 20771459

checkpoint_p1/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b12978be561a939d5e42acf2f7e6b4c850b5de037418d4796ea2a6d8cb27483
+size 20771459

checkpoint_p1/milestones/checkpoint_000007744_7929856.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b827c330088acf87846a22fcb713590d25472340de5a21eb5f4419ae73008fee
+size 20772379

checkpoint_p1/milestones/checkpoint_000015584_15958016.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da5e5f988097c92ff840a83f9b2510cf7177af01e9f8994466d8e0c16d6d20b
+size 20772435

checkpoint_p1/milestones/checkpoint_000023424_23986176.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30ec1869b0b17272cfd4c872647de1f1628daae816de1e72ce1bcfbb8388e9a0
+size 20772435

checkpoint_p1/milestones/checkpoint_000031296_32047104.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9ea9dd129d8599c6cbc0680b988003e6cd5ac76449018c116e3fff6b672bb3
+size 20772435

checkpoint_p1/milestones/checkpoint_000039136_40075264.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f87e257ebb7eb5668c147ada0b25da6f224a2b55016c1f9f8c7f22cbc4318d
+size 20772435

checkpoint_p1/milestones/checkpoint_000046976_48103424.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5800c353346173432437a19277f4ae66641704055579690a419437e71ccc03f
+size 20772435

checkpoint_p1/milestones/checkpoint_000054816_56131584.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696c4a7c73df7833223abe25fe4fdd077434202b6fce8ec335b99fda462a1e1e
+size 20772435

checkpoint_p1/milestones/checkpoint_000062656_64159744.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e751088f95330ab75a84309342f5900eae2e501fe61fb03fe8222eb1794d7337
+size 20772435

checkpoint_p1/milestones/checkpoint_000070528_72220672.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb74f51bc9b1cfd2a8e7f097bde3ad133677143faed939f901fe0262585d8b35
+size 20772435

checkpoint_p1/milestones/checkpoint_000078400_80281600.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a8cf42efa6e5225d2ece95e061fbfc97af82bd8c33cda4cc5d55a5400959cd
+size 20772435

checkpoint_p1/milestones/checkpoint_000086240_88309760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27bb0db6a0fcbf2400d9d027658dd897b3913c2e32caf96121c2a8890cd91e8a
+size 20772435

checkpoint_p1/milestones/checkpoint_000094080_96337920.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f3ff401fd7eb69f6d6f2efb95efa387dc4601ad1c594423f370a3b5c144d01e
+size 20772435

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_kongfumaster",
-  "experiment": "atari_kongfumaster",
+  "experiment": "atari_kongfumaster_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_kongfumaster",
   "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_kongfumaster --experiment=atari_kongfumaster --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_kongfumaster --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_kongfumaster --experiment=atari_kongfumaster_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_kongfumaster --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_kongfumaster",
-    "experiment": "atari_kongfumaster",
+    "experiment": "atari_kongfumaster_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_kongfumaster",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_kongfumaster_20230926_151629_795628"
+  "wandb_unique_id": "atari_kongfumaster_APPO_20231013_001150_943120"
 }

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 sha256:002089aa0970465a7f352621268d47d31d3e89d259d765930c16e586ecd18dd7
-size 6962393
+oid sha256:6610df1de1f9d179e8cb40c63bebf7eeb0a306ba8aee6d22da90fe54015daf00
+size 11835161