AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time

TL;DR

This paper introduces a novel approach combining Monte Carlo Tree Search (MCTS) with temporal difference learning, applied only at test time, enabling low-resource agents to outperform strong game programs on complex games.

Contribution

It presents a new architecture that integrates MCTS with TD learning agents only during testing, reducing training computational demands while maintaining high performance.

Findings

Agent beats strong Othello program Edax up to level 7

Achieves competitive results on ConnectFour and Rubik's Cube

Operates effectively on standard hardware without GPUs or TPUs

Abstract

Recently, the seminal algorithms AlphaGo and AlphaZero have started a new era in game learning and deep reinforcement learning. While the achievements of AlphaGo and AlphaZero - playing Go and other complex games at super human level - are truly impressive, these architectures have the drawback that they require high computational resources. Many researchers are looking for methods that are similar to AlphaZero, but have lower computational demands and are thus more easily reproducible. In this paper, we pick an important element of AlphaZero - the Monte Carlo Tree Search (MCTS) planning stage - and combine it with temporal difference (TD) learning agents. We wrap MCTS for the first time around TD n-tuple networks and we use this wrapping only at test time to create versatile agents that keep at the same time the computational demands low. We apply this new architecture to several complex games (Othello, ConnectFour, Rubik's Cube) and show the advantages achieved with this AlphaZero-inspired MCTS wrapper. In particular, we present results that this agent is the first one trained on standard hardware (no GPU or TPU) to beat the very strong Othello program Edax up to and including level 7 (where most other learning-from-scratch algorithms could only defeat Edax up to level 2).