Increasing-the-Action-Gap-RL-Pytorch. Pytorch implementation of the Persistent Advantage reinforcement learning operator proposed in paper 'Increasing the Action Gap: New Operators for Reinforcement Learning'. This repository includes source code for training, demo, action gap visualization and trained models for 5 Atari games.

Problem

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Audience

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Market

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Pricing

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.