Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1688632896.PC

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:971a4fd085a41df29bf7839f1e4e059767581778637ab9918949fb79f86a23c1
+size 40

.summary/0/events.out.tfevents.1688632907.PC

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b408e498d4059b65f67442ab08e1ccb0e85519b2d8b6c60f1e423c6a13401059
+size 40

.summary/0/events.out.tfevents.1688632944.PC

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cedb008478aba58fc6859fe3fd2e085d8d5f8827f98a2d4ff7e64b7049dd2448
+size 7939852

README.md

@@ -0,0 +1,56 @@
+---
+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_surround
+      type: atari_surround
+    metrics:
+    - type: mean_reward
+      value: nan +/- nan
+      name: mean_reward
+      verified: false
+---
+
+A(n) **APPO** model trained on the **atari_surround** 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 edbeeching/atari_2B_atari_surround_1111
+```
+
+    
+## Using the model
+
+To run the model after download, use the `enjoy` script corresponding to this environment:
+```
+python -m <path.to.enjoy.module> --algo=APPO --env=atari_surround --train_dir=./train_dir --experiment=atari_2B_atari_surround_1111
+```
+
+
+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 <path.to.train.module> --algo=APPO --env=atari_surround --train_dir=./train_dir --experiment=atari_2B_atari_surround_1111 --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_000746384_1528594432_reward_9.990.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65e6ccb7bd8d9339eaf266ebcfb1dffc83d5e1f36d04c2d0f687341874f1a750
+size 20715699

checkpoint_p0/checkpoint_000976608_2000093184.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3acf7298e4c0d2105f1e4461f30b985b353e99b4eed63a9d6ed50f8e81403ed0
+size 20716035

checkpoint_p0/checkpoint_000976624_2000125952.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41213da5244848d247a8369461333d7e14ae2f735488ce372d50b5a3b72da9c3
+size 20716035

checkpoint_p0/milestones/checkpoint_000063920_130908160.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705265243b22c5e42e0ded606043e121f3c26130095475edaa536c67f50d8c8f
+size 20717003

checkpoint_p0/milestones/checkpoint_000129488_265191424.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d2c7a91b42cc8692e40eb560cd18e7ef6b6092fb52fc4a2e396ca5075a8797
+size 20717003

checkpoint_p0/milestones/checkpoint_000195008_399376384.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b85945496b97f4a00c1e71fe0224b05e448ddc94ee3f639f97e157462908ad
+size 20717003

checkpoint_p0/milestones/checkpoint_000260352_533200896.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9234c54d3d3ed2f99d5f7e7747ce80d3d0d39d776fdbe1f4caacd5837a6d4801
+size 20717003

checkpoint_p0/milestones/checkpoint_000325696_667025408.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59ac256d05adf235ab6b9b24edaf03eb625a6813b26a68e1b967a26051308264
+size 20717003

checkpoint_p0/milestones/checkpoint_000391024_800817152.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d0498336eee4ea7477872882aef20c1a615d53a55402e268263b7b71a70039
+size 20717003

checkpoint_p0/milestones/checkpoint_000456448_934805504.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:007102c48f99c08d3b8d3edbf77647b6132aca1889373050df0e6ebc1bf29881
+size 20717003

checkpoint_p0/milestones/checkpoint_000521472_1067974656.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:435a26ab9f7bfce2fef493de3eccaef02a49b80032c6d4c1ac6b2f90a0be15cf
+size 20717059

checkpoint_p0/milestones/checkpoint_000586816_1201799168.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df573306b52b6a185f7470be5a13f6735790506b3b575386aafcbfec50be850f
+size 20717059

checkpoint_p0/milestones/checkpoint_000652288_1335885824.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18637187b32569cd5d39aecd722c79ad2130bb174aa31c6bf8ef934b9393dc6c
+size 20717059

checkpoint_p0/milestones/checkpoint_000717600_1469644800.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d1e215171fa08f2dfc3b2729f0fd963ddd6d8c0564ccb08f8ad8791425522b
+size 20717059

checkpoint_p0/milestones/checkpoint_000782080_1601699840.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c113f7063797c8473b972f4734a8970a38e97e0adc814d19915a7abb49d195c
+size 20717059

checkpoint_p0/milestones/checkpoint_000846240_1733099520.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e04a087eb095bf74653b300f1c8e4cb425113dac814cb81ddea55db9d351383c
+size 20717059

checkpoint_p0/milestones/checkpoint_000911616_1866989568.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432889e5aa5fff8878ee5abd82dda29a562fabe27c0d9849498860f2339c3c10
+size 20717059

config.json

@@ -0,0 +1,166 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "atari_surround",
+  "experiment": "20221014_2B__atari_surround_1111",
+  "train_dir": "train_dir/atari_2b",
+  "restart_behavior": "resume",
+  "device": "gpu",
+  "seed": 1111,
+  "num_policies": 1,
+  "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": 4,
+  "num_envs_per_worker": 1,
+  "batch_size": 1024,
+  "num_batches_per_epoch": 8,
+  "num_epochs": 2,
+  "rollout": 64,
+  "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": 1,
+  "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": 20,
+  "heartbeat_reporting_interval": 180,
+  "train_for_env_steps": 2000000000,
+  "train_for_seconds": 3600000,
+  "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": false,
+  "wandb_user": null,
+  "wandb_project": "sample_factory",
+  "wandb_group": null,
+  "wandb_job_type": "SF",
+  "wandb_tags": [],
+  "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,
+  "env_agents": 512,
+  "command_line": "--seed=1111 --experiment=20221014_2B__atari_surround_1111 --env=atari_surround --train_for_seconds=3600000 --algo=APPO --gamma=0.99 --num_workers=4 --num_envs_per_worker=1 --worker_num_splits=1 --env_agents=512 --benchmark=False --max_grad_norm=0.0 --decorrelate_experience_max_seconds=1 --encoder_conv_architecture=convnet_atari --encoder_conv_mlp_layers 512 --nonlinearity=relu --num_policies=1 --normalize_input=True --normalize_input_keys obs --normalize_returns=True --async_rl=True --batched_sampling=True --train_for_env_steps=2000000000 --save_milestones_sec=1200 --train_dir train_dir/atari_2b --rollout 64 --exploration_loss_coeff 0.0004677351413 --num_epochs 2 --batch_size 1024 --num_batches_per_epoch 8 --learning_rate 0.0003033891184",
+  "cli_args": {
+    "algo": "APPO",
+    "env": "atari_surround",
+    "experiment": "20221014_2B__atari_surround_1111",
+    "train_dir": "train_dir/atari_2b",
+    "seed": 1111,
+    "num_policies": 1,
+    "async_rl": true,
+    "batched_sampling": true,
+    "worker_num_splits": 1,
+    "num_workers": 4,
+    "num_envs_per_worker": 1,
+    "batch_size": 1024,
+    "num_batches_per_epoch": 8,
+    "num_epochs": 2,
+    "rollout": 64,
+    "gamma": 0.99,
+    "normalize_returns": true,
+    "exploration_loss_coeff": 0.0004677351413,
+    "max_grad_norm": 0.0,
+    "learning_rate": 0.0003033891184,
+    "normalize_input": true,
+    "normalize_input_keys": [
+      "obs"
+    ],
+    "decorrelate_experience_max_seconds": 1,
+    "train_for_env_steps": 2000000000,
+    "train_for_seconds": 3600000,
+    "save_milestones_sec": 1200,
+    "benchmark": false,
+    "encoder_conv_architecture": "convnet_atari",
+    "encoder_conv_mlp_layers": [
+      512
+    ],
+    "nonlinearity": "relu",
+    "env_agents": 512
+  },
+  "git_hash": "7e1e69550f4de4cdc003d8db5bb39e186803aee9",
+  "git_repo_name": "git@github.com:alex-petrenko/sample-factory.git"
+}

git.diff

@@ -0,0 +1,26 @@
+diff --git a/sf_examples/mujoco/experiments/mujoco_all_envs.py b/sf_examples/mujoco/experiments/mujoco_all_envs.py
+index 452c451a..a862b4c0 100644
+--- a/sf_examples/mujoco/experiments/mujoco_all_envs.py
++++ b/sf_examples/mujoco/experiments/mujoco_all_envs.py
+@@ -2,19 +2,13 @@ from sample_factory.launcher.run_description import Experiment, ParamGrid, RunDe
+ 
+ _params = ParamGrid(
+     [
+-        ("seed", [0, 1111, 2222, 3333, 4444, 5555, 6666, 7777, 8888, 9999]),
++        ("seed", [1111]),
+         (
+             "env",
+             [
+-                "mujoco_ant",
+-                "mujoco_halfcheetah",
+-                "mujoco_hopper",
+                 "mujoco_humanoid",
+-                "mujoco_doublependulum",
+-                "mujoco_pendulum",
++                "mujoco_standup",
+                 "mujoco_reacher",
+-                "mujoco_swimmer",
+-                "mujoco_walker",
+             ],
+         ),
+     ]