policy

tic-tac-toe-reinforced

alakhsharma22 · PyTorch

or hover any field below to flag it

Overview

Name
tic-tac-toe-reinforced
Author
alakhsharma22
Framework
PyTorch
License
unknown
Skill type
manipulation
Evidence level
untested
Task description
This project implements an AI-powered Tic-Tac-Toe game using Deep Learning and Minimax Algorithm. The AI can either learn from data using Reinforcement Learning or play optimally with the Minimax algorithm. The model is first trained using the imitation learning and then fine tuned by reinforcement

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 tic-tac-toe-reinforced yet.

Datasets that reference this policy

0

No datasets reference tic-tac-toe-reinforced yet.