Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1696966835.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f0934e8bf9c4a086378b6e236d99757e29f1d30ac5f54a86bb1f259df28089
+size 8041748

.summary/1/events.out.tfevents.1696966835.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d6d4d1aad21dad0bee576e9422b80b60518e20a50c59fb00b67809d4825089b
+size 4644650

README.md

@@ -15,7 +15,7 @@ model-index:
       type: atari_doubledunk
     metrics:
     - type: mean_reward
-      value: -11.20 +/- 6.40
+      value: -0.60 +/- 1.80
       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_doubledunk
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_doubledunk
 ```
 
     
+## 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_doubledunk --train_dir=./train_dir --experiment=appo-atari_doubledunk
+python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_doubledunk --train_dir=./train_dir --experiment=APPO-atari_doubledunk
 ```
 
 
@@ -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_doubledunk --train_dir=./train_dir --experiment=appo-atari_doubledunk --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.atari.train_atari --algo=APPO --env=atari_doubledunk --train_dir=./train_dir --experiment=APPO-atari_doubledunk --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_000094848_97124352_reward_-0.360.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0c0c1f1ea675e5fb507e6667b5110dcf748c890cd63c95b09291f4fb2c9125
+size 20795763

checkpoint_p0/checkpoint_000098304_100663296.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f366a2136d25cd4cae0c6571d47b7d264a4dd99c9369089900d1d229fad3b22
+size 20796099

checkpoint_p0/checkpoint_000098368_100728832.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc11218954565c2e6faac972f0f96eb3269b2e63bde1723208fc03879c8367a6
+size 20796099

checkpoint_p0/milestones/checkpoint_000007808_7995392.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45cfcbe5748307b3525e47d647af7d648bd23c627b3114f4e80155c881836ac0
+size 20796955

checkpoint_p0/milestones/checkpoint_000015776_16154624.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a425618c02a440000cc47d82792f786e5f3398a0b58aa34a3e0af73456ae1f
+size 20797011

checkpoint_p0/milestones/checkpoint_000023776_24346624.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b49d1dfde0676267b5a6a30492597ea6ef28c61af1a716eb13c80553365d26c6
+size 20797011

checkpoint_p0/milestones/checkpoint_000031808_32571392.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:180534bc86163bc8921f682cd4010f53f94faaaac8a911e87eec99110279270b
+size 20797011

checkpoint_p0/milestones/checkpoint_000039808_40763392.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13dbbe42266f83ea29209d63767c523362b6cc92a6da50448c5f818c49bc0364
+size 20797011

checkpoint_p0/milestones/checkpoint_000047808_48955392.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374d80458af364f2c8ee9b15ccf3bf4d15b096fb9f198c7469d80d592edf45dc
+size 20797011

checkpoint_p0/milestones/checkpoint_000055840_57180160.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bc389cda1834f37a5d26a3231a7481328534f5b3045d01d62a0c6f4657cf387
+size 20797011

checkpoint_p0/milestones/checkpoint_000063840_65372160.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a83b001a508787cc24361e9b555328639fdc73b7443769daab447dceade04877
+size 20797011

checkpoint_p0/milestones/checkpoint_000071840_73564160.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46d01a5dc92b1bd0b4b22490809238464108d6e5815a0cdd213ec0550b1c47ac
+size 20797011

checkpoint_p0/milestones/checkpoint_000079872_81788928.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cee8b6bfadea4409050030d9770f5ecb57bf999c203dfeee81e442e9a829440
+size 20797011

checkpoint_p0/milestones/checkpoint_000087904_90013696.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43da36d52d5fc8a4864bfe5c62f4d9c7e2f471da2e43366d0e8215bcf9f94789
+size 20797011

checkpoint_p0/milestones/checkpoint_000095904_98205696.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2694bd7a343c04d0f3af343c852fcaadd845bd37dd807df0df91f80e17f7e804
+size 20797011

checkpoint_p1/best_000090272_92438528_reward_22.880.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44a2907f7caf7cc158ae214e676f4918cb9bfdca5c1b8444c79d755e43e62847
+size 20795763

checkpoint_p1/checkpoint_000097632_99975168.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4532fac27a37e5f80b93fe07e7cc6249cb24a1f40d1f56b88b95e1f6ad5865
+size 20796099

checkpoint_p1/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f73c372c678ae0c5ffb18c89ebf20fda5ec62aefc9889198f3f28baeab99d6
+size 20796099

checkpoint_p1/milestones/checkpoint_000007840_8028160.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7956527d0c1c922324278293246be50dac77db8ab2efaeb343a48547b5859e
+size 20796955

checkpoint_p1/milestones/checkpoint_000015808_16187392.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c87a2e7197ed9380bb84348f8c5aff7036d1a78995303bdf15c122982d7534
+size 20797011

checkpoint_p1/milestones/checkpoint_000023744_24313856.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26f537524c8ab4e7cfa54457134353afaea23111b535b7762d944927d172a4d
+size 20797011

checkpoint_p1/milestones/checkpoint_000031680_32440320.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfa8e7208c0a32b9ee3e3a222cdef3106663677b6a74991cd2b4f7961baa48f2
+size 20797011

checkpoint_p1/milestones/checkpoint_000039616_40566784.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d951f0129ccb47636452586529a4699e16312ade2192675f4bb377a7ebd9f7
+size 20797011

checkpoint_p1/milestones/checkpoint_000047584_48726016.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0083aa46f2d28a9de21ec2d41d3e9e85aaeeb21e07800ee7ff412c16c3fda82c
+size 20797011

checkpoint_p1/milestones/checkpoint_000055552_56885248.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:683f2c7a485479023472628cb2d466f4b6672d27e54d59398fbfe7f5ec138c08
+size 20797011

checkpoint_p1/milestones/checkpoint_000063488_65011712.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6a7e4d3dfdf0650a6fcba2456eeb874bb39d6cd0848648fafde161c9769985
+size 20797011

checkpoint_p1/milestones/checkpoint_000071424_73138176.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d61ed3b9ce55cad45e050941bb294294de5b19e7d0d09f315d78197da1b6f57
+size 20797011

checkpoint_p1/milestones/checkpoint_000079360_81264640.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f383de0cfe340ded7a5ede483b7f1f4c8f453a580653227bea0679eae7e3b3
+size 20797011

checkpoint_p1/milestones/checkpoint_000087296_89391104.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3876a87623cb133625dd93b533ad535ea0e71f16502d5b9f920c43aa2ad78291
+size 20797011

checkpoint_p1/milestones/checkpoint_000095232_97517568.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:724578bff6bb5a8752b5323f351f2ce0056a4085b8af6526472421ec7ea1b454
+size 20797011

config.json

@@ -2,23 +2,23 @@
   "help": false,
   "algo": "APPO",
   "env": "atari_doubledunk",
-  "experiment": "atari_doubledunk",
+  "experiment": "atari_doubledunk_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_doubledunk",
   "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_doubledunk --experiment=atari_doubledunk --num_policies=2 --train_dir=./train_atari --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari --wandb_group=atari_doubledunk --wandb_job_type=SF --wandb_tags=atari",
+  "command_line": "--algo=APPO --env=atari_doubledunk --experiment=atari_doubledunk_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_doubledunk --wandb_job_type=SF --wandb_tags=atari",
   "cli_args": {
     "algo": "APPO",
     "env": "atari_doubledunk",
-    "experiment": "atari_doubledunk",
+    "experiment": "atari_doubledunk_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_doubledunk",
     "wandb_job_type": "SF",
     "wandb_tags": [
@@ -140,5 +158,5 @@
   },
   "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
   "git_repo_name": "not a git repository",
-  "wandb_unique_id": "atari_doubledunk_20230926_034120_891327"
+  "wandb_unique_id": "atari_doubledunk_APPO_20231010_204032_825502"
 }

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 sha256:7ab2bcf1d13ab08c4bb5b18eb51813c664e9f01362bf1e10eb2d517349742df6
-size 13943586
+oid sha256:0697101f1bc4bc04deebdd816982f2228200a555e0b8a8f7a75ac7bb4dd1bb6f
+size 13202730