Learning To Play Atari Games Using Dueling Q-Learning and Hebbian Plasticity

TL;DR

This paper explores advanced deep reinforcement learning techniques, including dueling Q-networks and Hebbian plasticity, to train neural agents for Atari games, emphasizing lifelong learning and adaptability.

Contribution

It introduces the integration of Hebbian plasticity into deep Q-learning architectures for Atari game agents, highlighting lifelong learning capabilities.

Findings

Plastic neural networks enable lifelong learning in Atari agents.

Dueling Q-networks improve training efficiency and performance.

Hebbian plasticity offers insights into adaptive neural mechanisms.

Abstract

In this work, an advanced deep reinforcement learning architecture is used to train neural network agents playing atari games. Given only the raw game pixels, action space, and reward information, the system can train agents to play any Atari game. At first, this system uses advanced techniques like deep Q-networks and dueling Q-networks to train efficient agents, the same techniques used by DeepMind to train agents that beat human players in Atari games. As an extension, plastic neural networks are used as agents, and their feasibility is analyzed in this scenario. The plasticity implementation was based on backpropagation and the Hebbian update rule. Plastic neural networks have excellent features like lifelong learning after the initial training, which makes them highly suitable in adaptive learning environments. As a new analysis of plasticity in this context, this work might provide valuable insights and direction for future works.