policy

reinforcementlearningmario

fahimaqil · PyTorch

or hover any field below to flag it

Overview

Name
reinforcementlearningmario
Author
fahimaqil
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
The aim of this project is to implement a state-of-the-art Deep Reinforcement Learning approach which is Proximal Policy Optimization (PPO) to train an agent to complete the first level of World 1 in Super Mario Bros.

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

20

Compatible environments

0

No environments list reinforcementlearningmario yet.

Datasets that reference this policy

0

No datasets reference reinforcementlearningmario yet.