Any-Play: An Intrinsic Augmentation for Zero-Shot Coordination

1 code implementation • 28 Jan 2022 • Keane Lucas, Ross E. Allen

Cooperative artificial intelligence with human or superhuman proficiency in collaborative tasks stands at the frontier of machine learning research.

Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi

no code implementations • NeurIPS 2021 • Ho Chit Siu, Jaime D. Pena, Edenna Chen, Yutai Zhou, Victor J. Lopez, Kyle Palko, Kimberlee C. Chang, Ross E. Allen

In addition to the game score, used as an objective metric of the human-AI team performance, we also quantify subjective measures of the human's perceived performance, teamwork, interpretability, trust, and overall preference of AI teammate.

Benchmarking reinforcement-learning +2

Health-Informed Policy Gradients for Multi-Agent Reinforcement Learning

1 code implementation • 2 Aug 2019 • Ross E. Allen, Jayesh K. Gupta, Jaime Pena, Yutai Zhou, Javona White Bear, Mykel J. Kochenderfer

This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function.

Multi-agent Reinforcement Learning Policy Gradient Methods +2