Instructions to use tsilva/Level2-1_stable-baselines3-ppo_4792f358 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use tsilva/Level2-1_stable-baselines3-ppo_4792f358 with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="tsilva/Level2-1_stable-baselines3-ppo_4792f358", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
Download model.json from tsilva/Level2-1_stable-baselines3-ppo_4792f358: direct link, hf CLI and curl.
- Browser
- Download file 7.15 kB
-
https://huggingface.co/tsilva/Level2-1_stable-baselines3-ppo_4792f358/resolve/main/model.json
- Command line
-
hf download hf://tsilva/Level2-1_stable-baselines3-ppo_4792f358/model.json
-
curl -L -o model.json https://huggingface.co/tsilva/Level2-1_stable-baselines3-ppo_4792f358/resolve/main/model.json
7.15 kB
| { | |
| "checkpoint": { | |
| "algorithm_id": "ppo", | |
| "filename": "model.zip", | |
| "kind": "checkpoint", | |
| "model_class": "stable_baselines3.ppo.ppo.PPO", | |
| "sha256": "0df684022632c2f14777a46f5705813c48252c5c6620bd9ccedc700070c63ac4", | |
| "size_bytes": 21054242, | |
| "step": 10000000 | |
| }, | |
| "document_type": "rlab.model", | |
| "format_version": 1, | |
| "policy": { | |
| "algorithm_id": "ppo", | |
| "model_class": "stable_baselines3.ppo.ppo.PPO", | |
| "training_backend_config_hash": "4a6293118b258140c5a2285db3a2d4e49bdf370706890b27bb462191edf67380", | |
| "training_backend_id": "sb3.ppo" | |
| }, | |
| "provenance": { | |
| "goal_slug": "Level2-1", | |
| "kind": "checkpoint", | |
| "metadata_version": 2, | |
| "queue_train_job_id": 7, | |
| "recipe_slug": "base", | |
| "repo_git_commit": "1e18630ff20f40c4038d6bee5b023ff704c7277b", | |
| "run_description": "Seed 1 runs the Level2-1 transfer of the successful Level1-1 B55 low-KL late-decay recipe, created to test whether that policy recipe transfers without changing PPO or reward hyperparameters while overriding only Level2-1 identity and reporting metadata.", | |
| "run_name": "Level2-1_base_s1_20260704T110948Z", | |
| "runtime_image_ref": "docker:ghcr.io/tsilva/gradlab/gradlab-train@sha256:d412737b5b53f2b07bae3f485a8cc3d58d5a5e9c28eb84b5fbd01e490f6a15f1", | |
| "seed": 1, | |
| "training_metadata": { | |
| "env_config": { | |
| "action_set": "simple", | |
| "clip_rewards": false, | |
| "completion_reward": 0.0, | |
| "death_penalty": 25.0, | |
| "done_on_events": [ | |
| "life_loss", | |
| "level_change" | |
| ], | |
| "env_provider": "supermariobrosnes-turbo", | |
| "env_threads": 4, | |
| "env_wrappers": [ | |
| { | |
| "id": "SuperMarioBrosNesProgressInfoWrapper", | |
| "kwargs": {} | |
| }, | |
| { | |
| "id": "SuperMarioBrosNesRewardEnvWrapper", | |
| "kwargs": { | |
| "completion_reward": 0.0, | |
| "death_penalty": 25.0, | |
| "progress_reward_scale": 1.0, | |
| "reward_mode": "score", | |
| "reward_scale": 10.0, | |
| "score_progress_clipped": false, | |
| "terminal_reward": 50.0 | |
| } | |
| } | |
| ], | |
| "frame_skip": 4, | |
| "game": "SuperMarioBros-Nes-v0", | |
| "hud_crop_top": -1, | |
| "info_events": {}, | |
| "max_episode_steps": 4500, | |
| "max_pool_frames": false, | |
| "no_progress_min_delta": 0, | |
| "no_progress_timeout_steps": 0, | |
| "obs_crop": [ | |
| 32, | |
| 0, | |
| 0, | |
| 0 | |
| ], | |
| "obs_resize_algorithm": "area", | |
| "observation_size": 84, | |
| "progress_reward_cap": 30.0, | |
| "progress_reward_scale": 1.0, | |
| "reward_mode": "score", | |
| "reward_scale": 10.0, | |
| "score_progress_clipped": false, | |
| "state": "Level2-1", | |
| "state_distribution": [], | |
| "state_probs": [], | |
| "state_sampling_mode": "single", | |
| "states": [], | |
| "sticky_action_prob": 0.0, | |
| "task_conditioning": false, | |
| "task_conditioning_info_values": [], | |
| "task_conditioning_info_vars": [], | |
| "terminal_reward": 50.0, | |
| "time_penalty": 0.0, | |
| "use_retro_reward": false | |
| }, | |
| "environment": { | |
| "env_id": "supermariobrosnes-turbo:SuperMarioBros-Nes-v0", | |
| "preprocessing": { | |
| "frame_skip": 4, | |
| "frame_stack": 4, | |
| "max_pool_frames": false, | |
| "obs_copy": "safe_view", | |
| "obs_crop": [ | |
| 32, | |
| 0, | |
| 0, | |
| 0 | |
| ], | |
| "obs_crop_fill": 0, | |
| "obs_crop_mode": "remove", | |
| "obs_grayscale": true, | |
| "obs_resize": [ | |
| 84, | |
| 84 | |
| ], | |
| "obs_resize_algorithm": "area", | |
| "pipeline": "supermariobrosnes_turbo_native_vec_env", | |
| "policy_observation_layout": "channel_first", | |
| "sticky_action_prob": 0.0 | |
| }, | |
| "provider_args": { | |
| "frame_stack": 4, | |
| "info": "data", | |
| "info_filter": "all", | |
| "inttype": "stable", | |
| "noop_reset_max": 0, | |
| "obs_copy": "safe_view", | |
| "obs_grayscale": true, | |
| "obs_layout": "chw", | |
| "obs_type": "image", | |
| "players": 1, | |
| "record": false, | |
| "render_mode": "rgb_array", | |
| "reward_clip": false, | |
| "rom_path": null, | |
| "scenario": "scenario", | |
| "use_restricted_actions": "filtered" | |
| }, | |
| "schema_version": 2, | |
| "state": "Level2-1", | |
| "task": { | |
| "action": { | |
| "set": "simple" | |
| }, | |
| "events": { | |
| "level_change": { | |
| "operation": "change", | |
| "signal": "level" | |
| }, | |
| "life_loss": { | |
| "operation": "decrease", | |
| "signal": "lives" | |
| } | |
| }, | |
| "id": "mario", | |
| "reward": { | |
| "clip_rewards": false, | |
| "completion_reward": 0.0, | |
| "death_penalty": 25.0, | |
| "progress_reward_cap": 30.0, | |
| "progress_reward_scale": 1.0, | |
| "reward_mode": "score", | |
| "reward_scale": 10.0, | |
| "score_progress_clipped": false, | |
| "terminal_reward": 50.0, | |
| "time_penalty": 0.0, | |
| "use_native_reward": false | |
| }, | |
| "signals": { | |
| "level": [ | |
| "levelHi", | |
| "levelLo" | |
| ], | |
| "lives": "lives", | |
| "score": "score", | |
| "x": [ | |
| "xscrollHi", | |
| "xscrollLo" | |
| ] | |
| }, | |
| "termination": { | |
| "failure": [ | |
| "life_loss" | |
| ], | |
| "max_episode_steps": 4500, | |
| "success": [ | |
| "level_change" | |
| ] | |
| } | |
| } | |
| }, | |
| "environment_hash": "sha256:31d6d9ced20024347d67573787dd6afe60053a82055a10a5e6951dfb591393ca", | |
| "preprocessing": { | |
| "frame_skip": 4, | |
| "frame_stack": 4, | |
| "max_pool_frames": false, | |
| "obs_copy": "safe_view", | |
| "obs_crop": [ | |
| 32, | |
| 0, | |
| 0, | |
| 0 | |
| ], | |
| "obs_crop_fill": 0, | |
| "obs_crop_mode": "remove", | |
| "obs_grayscale": true, | |
| "obs_resize": [ | |
| 84, | |
| 84 | |
| ], | |
| "obs_resize_algorithm": "area", | |
| "pipeline": "supermariobrosnes_turbo_native_vec_env", | |
| "policy_observation_layout": "channel_first", | |
| "sticky_action_prob": 0.0 | |
| }, | |
| "versions": { | |
| "stable_baselines3": "2.8.0", | |
| "stable_retro_turbo": "1.0.1.post5", | |
| "supermariobrosnes_turbo": "0.2.5" | |
| } | |
| }, | |
| "training_metadata_hash": "a4002644965876a6bb73b43e72cab350ab047ca0e6f7e01166cfb81598d4adae", | |
| "wandb_project": "SuperMarioBros-Nes-v0", | |
| "wandb_run_id": "osxjhs99", | |
| "wandb_run_path": "tsilva/SuperMarioBros-Nes-v0/osxjhs99" | |
| }, | |
| "recipe": { | |
| "document_type": "rlab.recipe", | |
| "filename": "recipe.json", | |
| "format_version": 1, | |
| "sha256": "07ffcde1a411e12955876ff5391d49daa6fe8b3b9ea4a4966b05c49e8888f810", | |
| "size_bytes": 10832 | |
| } | |
| } | |