Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games
Not on the map. Why?
Abstract (arXiv)
The combination of self-play and planning has achieved great successes in sequential games, for instance in Chess and Go. However, adapting algorithms such as AlphaZero to simultaneous games poses a new challenge. In these games, missing information about concurrent actions of other agents is a limiting factor as they may select different Nash equilibria or do not play optimally at all. Thus, it is vital to model the behavior of the other agents when interacting with them in simultaneous games. To this end, we propose Albatross: AlphaZero for Learning Bounded-rational Agents and Temperature-based Response Optimization using Simulated Self-play. Albatross learns to play the novel equilibrium concept of a Smooth Best Response Logit Equilibrium (SBRLE), which enables cooperation and competition with agents of any playing strength. We perform an extensive evaluation of Albatross on a set of cooperative and competitive simultaneous perfect-information games. In contrast to AlphaZero, Albatross is able to exploit weak agents in the competitive game of Battlesnake. Additionally, it yields an improvement of 37.6% compared to previous state of the art in the cooperative Overcooked benchmark.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 21 of its 67 references that are in the map. First posted on arXiv 5 Feb 2024.
Builds on
21 of 67 references.
References · 21
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2019Searching for MobileNetV3cited by 1,984
- 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
- 2017Population Based Training of Neural Networkscited by 351
- 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 345
- 2017Thinking Fast and Slow with Deep Learning and Tree Searchcited by 245
- 2020"Other-Play" for Zero-Shot Coordinationcited by 194
- 2021Collaborating with Humans without Human Datacited by 139
- 2018Deep Counterfactual Regret Minimizationcited by 102
- 2017Boltzmann Exploration Done Rightcited by 69
- 2021Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordinationcited by 69
- 2023Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biasedcited by 37
9 more
- 2023PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordinationcited by 25
- 2022PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaborationcited by 23
- 2021Model-Based Opponent Modelingcited by 21
- 2022Are AlphaZero-like Agents Robust to Adversarial Perturbations?cited by 14
- 2015Parameter estimation in softmax decision-making models with linear objective functionscited by 4
- 2020Battlesnake Challenge: A Multi-agent Reinforcement Learning Playground with Human-in-the-loopcited by 3
- 2020Complexity and Algorithms for Exploiting Quantal Opponents in Large Two-Player Gamescited by 3
- 2022POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learningcited by 3
- 2013Convergence of Monte Carlo Tree Search in Simultaneous Move Gamescited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.