Gymnasium environments for NES Mario games, with task metadata, reward instrumentation, and reproducible evaluation interfaces.
-
Updated
Sep 30, 2026 - Python
Gymnasium environments for NES Mario games, with task metadata, reward instrumentation, and reproducible evaluation interfaces.
send e-Reader card data to Super Mario Advance 4 over a link cable
World 1-1 cleared with unmodified Laya on DGX Spark. Model-driven jumping, replay-verified frames, and every decision recorded.
Auditable SMB3 agent experiments: planning, low-latency control, memory/physics research, and reproducible DQN evaluation.
Neural network plays Super Mario Bros. 3 using NEAT
Deep Q-Networks for Super Mario Bros 3, from a beginner-friendly basic implementation to advanced Rainbow-style improvements.
๐ 1988๋ NES ์ํผ๋ง๋ฆฌ์ค ๋ธ๋ผ๋์ค 3 100% ์์ ์น์ฑ ํฌํธ | ์ 8๊ฐ ์๋(World 1~8), ๋ชจ๋ ๋ณ์ ์ํธ(๋๊ตฌ๋ฆฌ, ๊ฐ๊ตฌ๋ฆฌ, ํ๋ํค, ํด๋จธ, P-๋ ๊ฐ, ์ ๋ฐ), 60FPS WebAssembly FCEUMM ์ฝ์ด, 2A03 APU 5์ฑ๋ ์ํฅ, ๊ฒ์ํจ๋/๋ชจ๋ฐ์ผ ํฐ์นํจ๋, 6์ฌ๋กฏ ๋น์ฃผ์ผ ์ธ์ด๋ธ, Game Genie ์นํธ ์์ง
To associate your repository with the super-mario-bros-3 topic, visit your repo's landing page and select "manage topics."