policy

RL-MsPacman-Agent

joelibaceta · Stable-Baselines3

or hover any field below to flag it

Overview

Name
RL-MsPacman-Agent
Author
joelibaceta
Framework
Stable-Baselines3
License
unknown
Skill type
other
Evidence level
untested
Task description
Deep Reinforcement Learning agent trained to play MsPacman using Gym Atari environments. Includes reward shaping, pathfinding (BFS), and training with Stable-Baselines3.

Spaces

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

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

0+20 mentioned but not in catalog yet

No robots list RL-MsPacman-Agent as compatible yet. Know of one? Flag it above.

Compatible environments

0

No environments list RL-MsPacman-Agent yet.

Datasets that reference this policy

0

No datasets reference RL-MsPacman-Agent yet.