Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1695148801.rhmmedcatt-ProLiant-ML350-Gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ae77b81a2f57513688c1595393f83ab53f74cb7360e0b93e91ed07b59b9435
+size 128503

.summary/0/events.out.tfevents.1695149023.rhmmedcatt-ProLiant-ML350-Gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dfdf9410d08a3870a2368adaacac535c6e0484eacafd82c3fe4daeda210912d
+size 1204245

.summary/1/events.out.tfevents.1695149023.rhmmedcatt-ProLiant-ML350-Gen10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06713145852614a5739893fff69a62790f19bea57a4a06af2872bda3c966886d
+size 948163

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: mujoco_pusher
+      type: mujoco_pusher
+    metrics:
+    - type: mean_reward
+      value: -28.51 +/- 2.05
+      name: mean_reward
+      verified: false
+---
+
+A(n) **APPO** model trained on the **mujoco_pusher** 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-mujoco-pusher
+```
+
+    
+## Using the model
+
+To run the model after download, use the `enjoy` script corresponding to this environment:
+```
+python -m sf_examples.mujoco.enjoy_mujoco --algo=APPO --env=mujoco_pusher --train_dir=./train_dir --experiment=appo-mujoco-pusher
+```
+
+
+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.mujoco.train_mujoco --algo=APPO --env=mujoco_pusher --train_dir=./train_dir --experiment=appo-mujoco-pusher --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_000019824_10149888_reward_-25.786.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d862fb3bf09a9c7602e8fe6769be64a8e960e89865fe07623d596d17f48794f4
+size 88575

checkpoint_p0/checkpoint_000021768_11145216.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80176197b4db8d2a20486da3d13fdc11906eadcb4a08e867d280e2dacefb64a
+size 88903

checkpoint_p0/checkpoint_000021824_11173888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9992236d4b3cdda79f6dc78f053a31aefa5bc2f94268dfe293adf4e45bb91f7
+size 88903

checkpoint_p1/best_000014336_7340032_reward_-30.173.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dad0351f76774fd253d67b2f7568511ced7e34e89b3e9b8c5d20d2cab3143ed
+size 88447

checkpoint_p1/checkpoint_000019480_9973760.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb35facde65c63890234a9b9254e4fa5c774a1277e5369afb4d945d5293c1323
+size 88775

checkpoint_p1/checkpoint_000019536_10002432.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae549b05451d88ae2b5b53ccc7b56b0593a02314abcd6010d84a09311f9984ef
+size 88775

config.json

@@ -0,0 +1,134 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "mujoco_pusher",
+  "experiment": "Pusher",
+  "train_dir": "./train_dir",
+  "restart_behavior": "resume",
+  "device": "gpu",
+  "seed": null,
+  "num_policies": 2,
+  "async_rl": false,
+  "serial_mode": false,
+  "batched_sampling": false,
+  "num_batches_to_accumulate": 2,
+  "worker_num_splits": 2,
+  "policy_workers_per_policy": 1,
+  "max_policy_lag": 1000,
+  "num_workers": 8,
+  "num_envs_per_worker": 8,
+  "batch_size": 1024,
+  "num_batches_per_epoch": 4,
+  "num_epochs": 2,
+  "rollout": 64,
+  "recurrence": 1,
+  "shuffle_minibatches": false,
+  "gamma": 0.99,
+  "reward_scale": 1,
+  "reward_clip": 1000.0,
+  "value_bootstrap": true,
+  "normalize_returns": true,
+  "exploration_loss_coeff": 0.0,
+  "value_loss_coeff": 1.3,
+  "kl_loss_coeff": 0.1,
+  "exploration_loss": "entropy",
+  "gae_lambda": 0.95,
+  "ppo_clip_ratio": 0.2,
+  "ppo_clip_value": 1.0,
+  "with_vtrace": false,
+  "vtrace_rho": 1.0,
+  "vtrace_c": 1.0,
+  "optimizer": "adam",
+  "adam_eps": 1e-06,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "max_grad_norm": 3.5,
+  "learning_rate": 0.00295,
+  "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": 1.0,
+  "normalize_input": true,
+  "normalize_input_keys": null,
+  "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": 20,
+  "heartbeat_reporting_interval": 180,
+  "train_for_env_steps": 10000000,
+  "train_for_seconds": 10000000000,
+  "save_every_sec": 15,
+  "keep_checkpoints": 2,
+  "load_checkpoint_kind": "latest",
+  "save_milestones_sec": -1,
+  "save_best_every_sec": 5,
+  "save_best_metric": "reward",
+  "save_best_after": 100000,
+  "benchmark": false,
+  "encoder_mlp_layers": [
+    64,
+    64
+  ],
+  "encoder_conv_architecture": "convnet_simple",
+  "encoder_conv_mlp_layers": [
+    512
+  ],
+  "use_rnn": false,
+  "rnn_size": 512,
+  "rnn_type": "gru",
+  "rnn_num_layers": 1,
+  "decoder_mlp_layers": [],
+  "nonlinearity": "tanh",
+  "policy_initialization": "torch_default",
+  "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": 1,
+  "env_framestack": 1,
+  "pixel_format": "CHW",
+  "use_record_episode_statistics": false,
+  "with_wandb": true,
+  "wandb_user": "matt-stammers",
+  "wandb_project": "sample_factory",
+  "wandb_group": "mujoco_pusher",
+  "wandb_job_type": "SF",
+  "wandb_tags": [
+    "mujoco"
+  ],
+  "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": "--env=mujoco_pusher --experiment=Pusher --train_dir=./train_dir",
+  "cli_args": {
+    "env": "mujoco_pusher",
+    "experiment": "Pusher",
+    "train_dir": "./train_dir"
+  },
+  "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
+  "git_repo_name": "not a git repository",
+  "wandb_unique_id": "Pusher_20230919_194340_581303"
+}