Modelpublic

tsilva/Level2-3_stable-baselines3-ppo_ff330a59

sourceHugging Facemitupdated 9d agoView on Hugging Face

0likes14downloads

Model Card

SuperMarioBros-Nes-v0 — Level2-3 — PPO

Stable-Baselines3 PPO policy for SuperMarioBros-Nes-v0 Level2-3, trained and evaluated with `rlab`.

At a Glance

Item	Value
Task	Complete `SuperMarioBros-Nes-v0` `Level2-3`
Provider	`supermariobrosnes-turbo`
Algorithm	`ppo`
Checkpoint	Step `4500000`
Evaluation	`stochastic` full evaluation, `100` episodes
Success	minimum `98.0%`, mean `98.0%`
Mean return	`3516.013`
Release	`v1`
Preview	Root `replay.mp4`
YouTube	Watch on YouTube

Quick Start

bash

git clone https://github.com/tsilva/rlab
cd rlab
git checkout 1e18630ff20f40c4038d6bee5b023ff704c7277b
uv sync --frozen

Import the ROM, then play or evaluate the immutable checkpoint:

bash

uv run rlab import-roms ~/roms --game SuperMarioBros-Nes-v0
uv run rlab play https://huggingface.co/tsilva/Level2-3_stable-baselines3-ppo_ff330a59/resolve/v1/model.zip
uv run rlab eval https://huggingface.co/tsilva/Level2-3_stable-baselines3-ppo_ff330a59/resolve/v1/model.zip

Evaluation

Action selection was stochastic under the published evaluation environment contract.

Start	Episodes	Successes	Success rate	Mean return
Level2-3	100	98	98.0%	3516.013

Environment and Policy Contract

Item	Value
Environment	`supermariobrosnes-turbo:SuperMarioBros-Nes-v0`
Environment hash	`sha256:1c0bc76e09b9e82e9505321e5592e136154236356c081c488c1bec49057f7d5a`
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}`
Action contract	`{"set":"simple"}`

Provenance

Item	Value
Source	rlab
Run	Level2-3_base_s1_20260704T121248Z
Recipe	`base`
Seed	`1`
Source commit	`1e18630ff20f40c4038d6bee5b023ff704c7277b`
Evaluated artifact	`tsilva/SuperMarioBros-Nes-v0/Level2-3_base_s1_20260704T121248Z-checkpoint:latest`

Files

File	Purpose
`model.zip`	Stable-Baselines3 policy checkpoint
`model.json`	Versioned checkpoint identity, policy type, provenance, and recipe binding
`recipe.json`	Versioned execution and evaluation contract
`release_manifest.json`	Release identity, evaluation evidence, and artifact hashes
`replay.mp4`	Browser-safe representative episode
`LICENSE`	License for rlab-authored policy weights and publication material

Limitations

Evaluation establishes performance only for the published environment hash, start distribution, policy preprocessing, and action-selection protocol. It does not establish generalization to other levels, environments, ROM revisions, or contracts.

Licensing

The rlab-authored policy weights and publication material are licensed under the MIT License in LICENSE. Emulator/runtime software and game assets remain governed by their own licenses and terms. This repository does not redistribute a game ROM.

Policy Lineage

This is a legacy rlab policy trained by Stable-Baselines3 PPO. It is not a GradLab-trained checkpoint and no GradLab compatibility is claimed.

—Trainer: Stable-Baselines3
—Algorithm: PPO
—Model class: stable_baselines3.ppo.ppo.PPO
—Full lineage digest: ff330a5907addffb33908b093445dbb9c23c01b7dd6e3f9dd95159fe73827d67
—Immutable release: hf://tsilva/Level2-3_stable-baselines3-ppo_ff330a59@v1
—Exact checkpoint tag: checkpoint-4500000

The mutable main branch contains this corrected card; the original v1 release files, commit, and tag remain unchanged.