Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners
arXiv:2004.13291
Abstract
Hanabi is a cooperative game that challenges exist-ing AI techniques due to its focus on modeling the mental states ofother players to interpret and predict their behavior. While thereare agents that can achieve near-perfect scores in the game byagreeing on some shared strategy, comparatively little progresshas been made in ad-hoc cooperation settings, where partnersand strategies are not known in advance. In this paper, we showthat agents trained through self-play using the popular RainbowDQN architecture fail to cooperate well with simple rule-basedagents that were not seen during training and, conversely, whenthese agents are trained to play with any individual rule-basedagent, or even a mix of these agents, they fail to achieve goodself-play scores.
References in corpus (9)
- Improving neural networks by preventing co-adaptation of feature detectors
- Playing Atari with Deep Reinforcement Learning
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
- Rainbow: Combining Improvements in Deep Reinforcement Learning
- Illuminating search spaces by mapping elites
- The Hanabi Challenge: A New Frontier for AI Research
- Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning
- "Other-Play" for Zero-Shot Coordination
- Re-determinizing Information Set Monte Carlo Tree Search in Hanabi