Population-based Evaluation In Repeated Rock-paper-scissors As A Benchmark For Multiagent Reinforcement Learning

Abstract

Progress in fields of machine learning and adversarial planning has benefited significantly from benchmark domains, from checkers and the classic UCI data sets to Go and Diplomacy. In sequential decision-making, agent evaluation has largely been restricted to few interactions against experts, with the aim to reach some desired level of performance (e.g. beating a human professional player). We propose a benchmark for multiagent learning based on repeated play of the simple game Rock, Paper, Scissors along with a population of forty-three tournament entries, some of which are intentionally sub-optimal. We describe metrics to measure the quality of agents based both on average returns and exploitability. We then show that several RL, online learning, and language model approaches can learn good counter-strategies and generalize well, but ultimately lose to the top-performing bots, creating an opportunity for research in multiagent learning.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylanctot2023population

Related papers

• Fightladder: A Benchmark For Competitive Multi-agent Reinforcement Learning (2024)0.00
• Reinforcing Competitive Multi-agents For Playing 'so Long Sucker' (2024)0.00
• Smacv2: An Improved Benchmark For Cooperative Multi-agent Reinforcement Learning (2022)5.24
• Reliable Validation Of Reinforcement Learning Benchmarks (2022)0.00
• Simplified Action Decoder For Deep Multi-agent Reinforcement Learning (2019)4.03
• Policy Evaluation And Seeking For Multi-agent Reinforcement Learning Via Best Response (2020)0.00
• Mimicking To Dominate: Imitation Learning Strategies For Success In Multiagent Competitive Games (2023)0.00
• Actor-critic Policy Optimization In Partially Observable Multiagent Environments (2018)0.00