An open API service indexing awesome lists of open source software.

https://github.com/florianvazelle/unity-rl

Markov Decision Process and Temporal Difference algorithms
https://github.com/florianvazelle/unity-rl

gridworld markov-decision-processes monte-carlo qlearning reinforcement-learning sarsa sokoban tictactoe unity

Last synced: 10 months ago
JSON representation

Markov Decision Process and Temporal Difference algorithms

Awesome Lists containing this project

README

          

# Unity RL

Unity RL is a Unity C# application with multiple implementations of reinforcement learning algorithms on three mini-games.

## Setup

This project work on Unity 2019.4.14f1

## Table of Contents

### Algorithms

- Markov Decision Process
- [Policy Iteration](https://github.com/florianvazelle/LIN_THENEVIN_VAZELLE_5ADJV_RL/blob/main/Assets/Scripts/Algo/Markov/MarkovPolicy.cs)
- [Value Iteration](https://github.com/florianvazelle/LIN_THENEVIN_VAZELLE_5ADJV_RL/blob/main/Assets/Scripts/Algo/Markov/MarkovValue.cs)
- [Monte Carlo](https://github.com/florianvazelle/LIN_THENEVIN_VAZELLE_5ADJV_RL/blob/main/Assets/Scripts/Algo/TemporalDifference/MonteCarlo.cs)
- Exploring Starts
- On Policy (first/evry visit)
- Off Policy (first/evry visit)
- Temporal Difference
- [SARSA](https://github.com/florianvazelle/LIN_THENEVIN_VAZELLE_5ADJV_RL/blob/main/Assets/Scripts/Algo/TemporalDifference/SARSA.cs)
- [QLearning](https://github.com/florianvazelle/LIN_THENEVIN_VAZELLE_5ADJV_RL/blob/main/Assets/Scripts/Algo/TemporalDifference/QLearning.cs)

### Games

- [Grid World](https://github.com/florianvazelle/LIN_THENEVIN_VAZELLE_5ADJV_RL/blob/main/Assets/Scripts/Game/GridWorld/GridWorld.cs)
- [Tic Tac Toe](https://github.com/florianvazelle/LIN_THENEVIN_VAZELLE_5ADJV_RL/blob/main/Assets/Scripts/Game/TicTacToe/TicTacToe.cs)
- [Sokoban](https://github.com/florianvazelle/LIN_THENEVIN_VAZELLE_5ADJV_RL/blob/main/Assets/Scripts/Game/Sokoban/Sokoban.cs)

## Demos