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.1697241684.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2bc4323b89c112bcae9596874f4fce71897079ae67903bd14e91a6b073da45c
+size 7758396

.summary/1/events.out.tfevents.1697241684.rhmmedcatt-proliant-ml350-gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:633dcabc80f8436708d844a1a7b7f28739b24993799fe70c61deaab903c05f84
+size 4486599

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_pong
+      type: atari_pong
+    metrics:
+    - type: mean_reward
+      value: 21.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+A(n) **APPO** model trained on the **atari_pong** 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_pong
+```
+
+    
+## 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_pong --train_dir=./train_dir --experiment=APPO-atari_pong
+```
+
+
+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_pong --train_dir=./train_dir --experiment=APPO-atari_pong --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_000017536_17956864_reward_21.000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bea8a9283c702d42f2e75d580cf17c85572279bca40b79cdb66feecc703545c
+size 20721843

checkpoint_p0/checkpoint_000097376_99713024.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9b021a1dd4e2cce50550480b42f35a5afdf1a0ed634297d3f420c8768ad3b2
+size 20722179

checkpoint_p0/checkpoint_000097664_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4296048e9d67250825be6d505550a86c38026ded10e1da33d9576eb9daa83313
+size 20722179

checkpoint_p0/milestones/checkpoint_000008128_8323072.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afe0a9da532a79d71aaea1665e6f6ea8f29159a9cf4f861ce6f6175e52199e8
+size 20723035

checkpoint_p0/milestones/checkpoint_000016416_16809984.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8fe29687469d871f556020c9b511acbf86e6deb87a1a6258bba585328cba1ae
+size 20723091

checkpoint_p0/milestones/checkpoint_000024672_25264128.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a129e12f7369afe9e1ee35d96b3e4fb506d3600bfa1f94674441e58b6384e7
+size 20723091

checkpoint_p0/milestones/checkpoint_000032928_33718272.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ea87f127ae78ca6894ad9a015332d9698a469713dc42ddc84ddcbf1bde95a1
+size 20723091

checkpoint_p0/milestones/checkpoint_000041184_42172416.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b20f6f9ce970ff3447c3c72c86164986c9ef4d0600f98617bf4facee5e148c
+size 20723091

checkpoint_p0/milestones/checkpoint_000049440_50626560.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4fc305f167a1f96356aace3eaacd4a973d0375df614899a63729376b3663d64
+size 20723091

checkpoint_p0/milestones/checkpoint_000057696_59080704.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fabaa0a7c1f003f59da01d7db07210b1b3d6b3572c9960cda13ec8a1344a6760
+size 20723091

checkpoint_p0/milestones/checkpoint_000065984_67567616.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93141a6d95df1c5693612169d47b93eb1edc733017a894ac4cc5cec4f0cf7413
+size 20723091

checkpoint_p0/milestones/checkpoint_000074240_76021760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c18028b72a499c53569b9fda1f40ad2267410f27e970e121a1875a772c1b766
+size 20723091

checkpoint_p0/milestones/checkpoint_000082496_84475904.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1d29131a5811f0578f0d65f947d9ed311e84b5dc12802fd2df7e12ec213dbe
+size 20723091

checkpoint_p0/milestones/checkpoint_000090784_92962816.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45f4fcd2b227647812b1006c2c46a59948cdf3bfff73b9ffd101b281e2d0f451
+size 20723091

checkpoint_p1/best_000023872_24444928_reward_21.000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:623ade3f8390a9bd80c4227be3ef1fe4a8986f9edb31b0d28e0c2f1aaeb794aa
+size 20721843

checkpoint_p1/checkpoint_000098272_100630528.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73463b6e7c26275617358613d1731bbfe66c283af6885f2fe2ddec7129d6d3c1
+size 20722179

checkpoint_p1/checkpoint_000098560_100925440.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ac30cb2a4008739380d96e5bcb1da4798f73f94f6e8b256b30db96a3a9cca7
+size 20722179

checkpoint_p1/milestones/checkpoint_000008192_8388608.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d97af8d4e08ac86de98ec1eb569fa0f46d7c5679ec53f9f62472b2cd292f68
+size 20723035

checkpoint_p1/milestones/checkpoint_000016544_16941056.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd42f99c7e25b3f8d00c3a972e2490f6a4b040d1b8b66a928f3798b06a12a0b
+size 20723091

checkpoint_p1/milestones/checkpoint_000024896_25493504.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a56749f3f6dec3a90cb63c5f1762814a80aebc2f23542d521f8baee165b5a21
+size 20723091

checkpoint_p1/milestones/checkpoint_000033216_34013184.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1265ffdeda73b3c9f42728aa5c98c290e256672552c55afd578dfe93a51cd6d0
+size 20723091

checkpoint_p1/milestones/checkpoint_000041568_42565632.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c90f6c8cfce6f8c6eebf51b080d268c405ec7f1d74a4346d8313357140b6f5
+size 20723091

checkpoint_p1/milestones/checkpoint_000049888_51085312.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c847b5b2a59b9e0562df4a819f6a9b6930b3ccadb6690c3b8527e708c4b7de6
+size 20723091

checkpoint_p1/milestones/checkpoint_000058240_59637760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcfc70035e1cda003ce7b1e84cc48720f2456495603c261fa10e59c1d8ee51bc
+size 20723091

checkpoint_p1/milestones/checkpoint_000066592_68190208.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74fa9404090705002ff95ebdf7db7be2951a08c3d5892c713eaff4fbbad70717
+size 20723091

checkpoint_p1/milestones/checkpoint_000074912_76709888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:531b15ec146cbbf735004c1b083788bc818377f1537893fefd2ab4f636d6a63a
+size 20723091

checkpoint_p1/milestones/checkpoint_000083264_85262336.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55116c297c0ab83e0e94510ab15f5662aff73313607ae5782852a59da80bb59
+size 20723091

checkpoint_p1/milestones/checkpoint_000091584_93782016.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12c6787fc282ace746489ba1cfc8b23662c45e653b465dba910a4dfa30a87fe
+size 20723091

config.json

@@ -0,0 +1,162 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "atari_pong",
+  "experiment": "atari_pong_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_pong",
+  "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_pong --experiment=atari_pong_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_pong --wandb_job_type=SF --wandb_tags=atari",
+  "cli_args": {
+    "algo": "APPO",
+    "env": "atari_pong",
+    "experiment": "atari_pong_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_pong",
+    "wandb_job_type": "SF",
+    "wandb_tags": [
+      "atari"
+    ]
+  },
+  "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
+  "git_repo_name": "not a git repository",
+  "wandb_unique_id": "atari_pong_APPO_20231014_010121_934395"
+}

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 sha256:9b1094370291aafb4203456e1cba9aa19daa06f2cab35ebc9fc726ec0d563df9
+size 1382728