7 papers
Modular Discovery of General Game-Playing Algorithms with Large Language Models
Zun Li, John Schultz, Marc Lanctot +1
General Game Playing across arbitrary games from rules alone remains challenging due to differing algorithmic requirements across game classes and strict decision-time constraints.…
Game Arena: Strategic LLM Evaluation in Competitive Environments
Bovard Doerschuk-Tiberi, Yao Yan, Justin Chiu +59
We introduce Kaggle Game Arena, an open and ever-expanding platform to evaluate large language models (LLMs) through competitive games. Different from static benchmarks, game arena…
Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models
Daniel Hennes, Zun Li, John Schultz +1
Recent advances in multi-agent reinforcement learning, particularly Policy-Space Response Oracles (PSRO), have enabled the computation of approximate game-theoretic equilibria in i…
Active Evaluation of General Agents: Problem Definition and Comparison of Baseline Algorithms
Marc Lanctot, Kate Larson, Ian Gemp +1
As intelligent agents become more generally-capable, i.e. able to master a wide variety of tasks, the complexity and cost of properly evaluating them rises significantly. Tasks tha…
Discovering Multiagent Learning Algorithms with Large Language Models
Zun Li, John Schultz, Daniel Hennes +1
Much of the advancement in Multi-Agent Reinforcement Learning (MARL) for imperfect-information games has historically depended on the manual, iterative refinement of algorithmic ba…
Code World Models for General Game Playing
Wolfgang Lehrach, Daniel Hennes, Miguel Lazaro-Gredilla +13
Large Language Models (LLMs) reasoning abilities are increasingly being applied to classical board and card games, but the dominant approach -- involving prompting for direct move…
Jackpot! Alignment as a Maximal Lottery
Roberto-Rafael Maura-Rivero, Marc Lanctot, Francesco Visin +1
Reinforcement Learning from Human Feedback (RLHF), the standard for aligning Large Language Models (LLMs) with human values, is known to fail to satisfy properties that are intuiti…