Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC

TL;DR

This paper introduces 'Beyond The Rainbow' (BTR), a high-performance deep reinforcement learning algorithm that achieves state-of-the-art results on Atari and complex 3D games using only a desktop PC, emphasizing efficiency and robustness.

Contribution

BTR integrates six RL improvements into Rainbow DQN, setting new performance benchmarks and demonstrating versatility across different game environments with minimal computational resources.

Findings

Achieved a human-normalized IQM of 7.4 on Atari-60.

Successfully trained agents on 3D games like Super Mario Galaxy, Mario Kart, and Mortal Kombat.

Trained agents on 200 million Atari frames within 12 hours on a desktop PC.

Abstract

Rainbow Deep Q-Network (DQN) demonstrated combining multiple independent enhancements could significantly boost a reinforcement learning (RL) agent's performance. In this paper, we present "Beyond The Rainbow" (BTR), a novel algorithm that integrates six improvements from across the RL literature to Rainbow DQN, establishing a new state-of-the-art for RL using a desktop PC, with a human-normalized interquartile mean (IQM) of 7.4 on Atari-60. Beyond Atari, we demonstrate BTR's capability to handle complex 3D games, successfully training agents to play Super Mario Galaxy, Mario Kart, and Mortal Kombat with minimal algorithmic changes. Designing BTR with computational efficiency in mind, agents can be trained using a high-end desktop PC on 200 million Atari frames within 12 hours. Additionally, we conduct detailed ablation studies of each component, analyzing the performance and impact using numerous measures. Code is available at https://github.com/VIPTankz/BTR.