Delta Schema Network in Model-based Reinforcement Learning

TL;DR

This paper introduces Delta Schema Networks, an extension of schema networks for model-based reinforcement learning, demonstrating improved transfer learning capabilities in Atari games.

Contribution

It presents new algorithms for training DSNs, predicting future states, and planning actions, advancing transfer learning in reinforcement learning environments.

Findings

DSN achieves strong transfer learning performance on Atari games.

The proposed algorithms effectively predict future states and plan actions.

Enhanced transfer learning efficiency over existing methods.

Abstract

This work is devoted to unresolved problems of Artificial General Intelligence - the inefficiency of transfer learning. One of the mechanisms that are used to solve this problem in the area of reinforcement learning is a model-based approach. In the paper we are expanding the schema networks method which allows to extract the logical relationships between objects and actions from the environment data. We present algorithms for training a Delta Schema Network (DSN), predicting future states of the environment and planning actions that will lead to positive reward. DSN shows strong performance of transfer learning on the classic Atari game environment.