Evaluating The Rainbow DQN Agent In Hanabi With Unseen Partners

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keycanaan2020evaluating

Related papers

• Theory Of Mind For Deep Reinforcement Learning In Hanabi (2021)0.00
• Behavioral Differences Is The Key Of Ad-hoc Team Cooperation In Multiplayer Games Hanabi (2023)0.00
• Evaluation Of Human-ai Teams For Learned And Rule-based Agents In Hanabi (2021)0.00
• Reinforcement Learning On Human Decision Models For Uniquely Collaborative AI Teammates (2021)0.00
• Simplified Action Decoder For Deep Multi-agent Reinforcement Learning (2019)4.03
• Is Vanilla Policy Gradient Overlooked? Analyzing Deep Reinforcement Learning For Hanabi (2022)0.00
• Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In The Game Of Hanabi (2023)0.00
• Learn To Interpret Atari Agents (2018)0.00