Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+git.diff filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

.summary/0/events.out.tfevents.1696747807.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e866594c9dc30e926418e722a3a4fd6eca8ae6b3f2c35b8e04256e03030678e
+size 7528010

.summary/1/events.out.tfevents.1696747807.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71670cbfbeef5e86d88d93744d932af9869915a226995cbb79e8db6033d4bdbe
+size 4355990

README.md

@@ -0,0 +1,169 @@
+---
+library_name: sample-factory
+tags:
+- deep-reinforcement-learning
+- reinforcement-learning
+- sample-factory
+model-index:
+- name: APPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: atari_asterix
+      type: atari_asterix
+    metrics:
+    - type: mean_reward
+      value: 14800.00 +/- 10461.83
+      name: mean_reward
+      verified: false
+---
+
+A(n) **APPO** model trained on the **atari_asterix** environment.
+
+This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
+Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
+
+
+## Downloading the model
+
+After installing Sample-Factory, download the model with:
+```
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_asterix
+```
+
+    
+## 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_asterix --train_dir=./train_dir --experiment=APPO-atari_asterix
+```
+
+
+You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
+See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
+    
+## Training with this model
+
+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_asterix --train_dir=./train_dir --experiment=APPO-atari_asterix --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_000091072_93257728_reward_40.890.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d0d8b26a75bf9f375d6c9e0cd03d5e430f33d9a1fade6b2aa313876091456b
+size 20740275

checkpoint_p0/checkpoint_000097792_100139008.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04bd1640ae685f668c143c2474f9764a8f3245fb493b902ad67e2f1617b92557
+size 20740611

checkpoint_p0/checkpoint_000098144_100499456.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d8fe9de9336e5cd869563a7f403be4a31c5c67dab0af5aecf52b70754472a6
+size 20740611

checkpoint_p0/milestones/checkpoint_000008416_8617984.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22841dee48b300dc96a4847bb5d345c70e899bcdc763e3861e24c763301b853e
+size 20741467

checkpoint_p0/milestones/checkpoint_000016960_17367040.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd005a02db925d77c74341241df916ac1270512779e3247b6643f0c512f2f75
+size 20741523

checkpoint_p0/milestones/checkpoint_000025568_26181632.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e1fcea59cc8fee2c3685ebd3ff7e759362981f3de3279105cd888ef5ebf1cf
+size 20741523

checkpoint_p0/milestones/checkpoint_000034176_34996224.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f002c4a62882ee197f69fac8c8b253de4039d90c5fec6eaf891958479b6f1f
+size 20741523

checkpoint_p0/milestones/checkpoint_000042784_43810816.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94dd1e705d9f621acda45798cadde8f31b089d15e12d5e223a149e72709b970
+size 20741523

checkpoint_p0/milestones/checkpoint_000051328_52559872.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c232ba29be5351a623cc817ed9ef93eddce104ac5141e2ab1821c9e204f8ad
+size 20741523

checkpoint_p0/milestones/checkpoint_000059936_61374464.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9268f9255cecfecb79232d4463ae1208124fa7c658498fb41d72abe79c9cc6
+size 20741523

checkpoint_p0/milestones/checkpoint_000068512_70156288.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c66f0c662ed6ce1a95758ea461d5f15a0081191f37728a0547ccfd493f386cd
+size 20741523

checkpoint_p0/milestones/checkpoint_000077120_78970880.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6e20c37cd51346a0a9a43a7625b5794fc4474497a973428dbef6d72aafc8c4
+size 20741523

checkpoint_p0/milestones/checkpoint_000085760_87818240.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2513fb1f79fc508b346ee39d81fd206435e353fa2b6c0646c873c42ef04859cd
+size 20741523

checkpoint_p0/milestones/checkpoint_000094336_96600064.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863075962b0bc7143b3211148e8f7aeee2e2f147a71f01095fcab1736bed6fdd
+size 20741523

checkpoint_p1/best_000097280_99614720_reward_44.650.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbda331cc752f528237e62e4edee4944c7edec283b8ad9ee8592aa46458e113
+size 20740275

checkpoint_p1/checkpoint_000097312_99647488.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b515df11f44b090cc917fe1a472a26b7738fcc39ae9482b06df4541b2abc15
+size 20740611

checkpoint_p1/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:215b2ea50132ec511848df2426df713c1e63cdccb2fe7ac715cee5d1ef10a08e
+size 20740611

checkpoint_p1/milestones/checkpoint_000008352_8552448.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f3c7a6cd7127308e7a36cd8e93e7a5dfda76738a4a8ecfa85cd26820cd17a20
+size 20741467

checkpoint_p1/milestones/checkpoint_000016896_17301504.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b754c2eabb52d7a99e4d8b0ab4c1a5f28b5fab597a2aa7150f10ebd4bc8821
+size 20741523

checkpoint_p1/milestones/checkpoint_000025440_26050560.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f575a970a1848106649b8c8b80d11c00c8e8371eb827b7a13c8b096235d91c
+size 20741523

checkpoint_p1/milestones/checkpoint_000034016_34832384.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61789aff687e80ffcfcb7daf79e22c62383e2f13c21645c02cfe7b095441afac
+size 20741523

checkpoint_p1/milestones/checkpoint_000042560_43581440.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3aeac808ebb2249e0d1348154129ea9d38c026e0b8c0aab1bf3edb39fb8fa44
+size 20741523

checkpoint_p1/milestones/checkpoint_000051104_52330496.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e012493557f3c64fe2a1e7979e7251504fbbcee2f1736aafcad278bf2f942e31
+size 20741523

checkpoint_p1/milestones/checkpoint_000059648_61079552.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17558fc8f22e1833c12649fe23c11aec94b896c78e17e6cda9ddf0b9277be336
+size 20741523

checkpoint_p1/milestones/checkpoint_000068224_69861376.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fdfaf4bfb38e09557568e16d7c2d0a92df1121d8bfaaf82c11c34a82762696a
+size 20741523

checkpoint_p1/milestones/checkpoint_000076768_78610432.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f00e7ad6bca026b13deac6bcb2a0c2e1c6486c672b54400d6a4c719c9b0eba
+size 20741523

checkpoint_p1/milestones/checkpoint_000085344_87392256.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa858674562b483547fe55deb405c18f68df8393c30ed4c4b177aae8d78ed957
+size 20741523

checkpoint_p1/milestones/checkpoint_000093888_96141312.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a53ad4d041d31468cbaa1c221f687d438f684eaeef811053efb9cd967c59fb5
+size 20741523

config.json

@@ -0,0 +1,162 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "atari_asterix",
+  "experiment": "atari_asterix_APPO",
+  "train_dir": "./train_atari",
+  "restart_behavior": "restart",
+  "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,
+  "pixel_format": "CHW",
+  "use_record_episode_statistics": true,
+  "with_wandb": true,
+  "wandb_user": "matt-stammers",
+  "wandb_project": "atari_APPO",
+  "wandb_group": "atari_asterix",
+  "wandb_job_type": "SF",
+  "wandb_tags": [
+    "atari"
+  ],
+  "with_pbt": false,
+  "pbt_mix_policies_in_one_env": true,
+  "pbt_period_env_steps": 5000000,
+  "pbt_start_mutation": 20000000,
+  "pbt_replace_fraction": 0.3,
+  "pbt_mutation_rate": 0.15,
+  "pbt_replace_reward_gap": 0.1,
+  "pbt_replace_reward_gap_absolute": 1e-06,
+  "pbt_optimize_gamma": false,
+  "pbt_target_objective": "true_objective",
+  "pbt_perturb_min": 1.1,
+  "pbt_perturb_max": 1.5,
+  "command_line": "--algo=APPO --env=atari_asterix --experiment=atari_asterix_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_asterix --wandb_job_type=SF --wandb_tags=atari",
+  "cli_args": {
+    "algo": "APPO",
+    "env": "atari_asterix",
+    "experiment": "atari_asterix_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_APPO",
+    "wandb_group": "atari_asterix",
+    "wandb_job_type": "SF",
+    "wandb_tags": [
+      "atari"
+    ]
+  },
+  "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
+  "git_repo_name": "not a git repository",
+  "wandb_unique_id": "atari_asterix_APPO_20231008_075004_357423"
+}

git.diff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3357904f421d3f4924836316b1741bf64d5dd0e807d5e80ac07059b4c52a7008
+size 14426734

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4892f6c3fa69ff9f157bd69b450237b96c02eb18b707ab8a7e00b37e12b5a2f9
+size 3889614