# Upside-Down-Reinforcement-Learning

**Repository Path**: isaaclin007/Upside-Down-Reinforcement-Learning

## Basic Information

- **Project Name**: Upside-Down-Reinforcement-Learning
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-04-19
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Upside-Down-Reinforcement-Learning

Upside-Down Reinforcement Learning (⅂ꓤ) implementation in Pytorch. <br/>
Based on the paper published by *Jürgen Schmidhuber*: [⅂ꓤ-Paper](https://github.com/BY571/Upside-Down-Reinforcement-Learning/tree/master/paper)

Currently this repository contains only a discrete action space implementation for the OpenAI gym CartPole environment.

The notebook includes the training of a behavior function as well as an evaluation part, where you can test the trained behavior function. Feed it with an **desired reward** that the agent shall achieve in a **desired time horizon**.


## Plots for the CartPole Environment:
![plot](imgs/Graph.png)

ToDo: Continuous action space implementation.