An Evolutionary Framework For Connect-4 As Test-bed For Comparison Of Advanced Minimax, Q-learning And MCTS

Abstract

A major challenge in decision making domains with large state spaces is to effectively select actions which maximize utility. In recent years, approaches such as reinforcement learning (RL) and search algorithms have been successful to tackle this issue, despite their differences. RL defines a learning framework that an agent explores and interacts with. Search algorithms provide a formalism to search for a solution. However, it is often difficult to evaluate the performances of such approaches in a practical way. Motivated by this problem, we focus on one game domain, i.e., Connect-4, and develop a novel evolutionary framework to evaluate three classes of algorithms: RL, Minimax and Monte Carlo tree search (MCTS). The contribution of this paper is threefold: i) we implement advanced versions of these algorithms and provide a systematic comparison with their standard counterpart, ii) we develop a novel evaluation framework, which we call the Evolutionary Tournament, and iii) we conduct

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytaylor2024an

Related papers

• Monte Carlo Q-learning For General Game Playing (2018)0.00
• Population-based Evaluation In Repeated Rock-paper-scissors As A Benchmark For Multiagent Reinforcement Learning (2023)0.00
• Decision Making In Non-stationary Environments With Policy-augmented Monte Carlo Tree Search (2022)0.00
• Multiple Policy Value Monte Carlo Tree Search (2019)0.00
• Learning Policies From Self-play With Policy Gradients And MCTS Value Estimates (2019)0.00
• Ordinal Monte Carlo Tree Search (2019)0.00
• Convex Regularization In Monte-carlo Tree Search (2020)0.00
• Frontier Coding Agents Can Now Implement An Alphazero Self-play Machine Learning Pipeline For Connect Four That Performs Comparably To An External Solver (2026)0.00