Skip to content

Mario_RL is a course project developing a reinforcement learning (RL) agent for Super Mario Bros. It focuses on boosting agent performance via observation/action/reward space feature engineering (not advanced RL tweaks), using the DI-adventure baseline.

Notifications You must be signed in to change notification settings

secretsites/Mario_RL

Repository files navigation

Mario_RL

Mario_RL is a course project developing a reinforcement learning (RL) agent for Super Mario Bros. It focuses on boosting agent performance via observation/action/reward space feature engineering (not advanced RL tweaks), using the DI-adventure baseline.

tasks

review DQN-related papers, use gym-super-mario-bros v0, run/evaluate baseline (PyTorch), test feature processing, analyze performance. Deliverables: report, A0 poster, code package. It requires online RL learning without pre-trained models/imitation data.

About

Mario_RL is a course project developing a reinforcement learning (RL) agent for Super Mario Bros. It focuses on boosting agent performance via observation/action/reward space feature engineering (not advanced RL tweaks), using the DI-adventure baseline.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages