Learning to Trust: Bayesian Adaptation to Varying Suggester Reliability in Sequential Decision Making
This work addresses the challenge of suggestion uncertainty for autonomous agents in uncertain environments, providing a foundation for adaptive human-agent collaboration, though it is incremental as it builds on existing methods for incorporating advice.
The paper tackles the problem of autonomous agents incorporating external action suggestions with varying reliability in sequential decision-making under uncertainty, and introduces a framework that dynamically learns and adapts to suggester reliability through Bayesian inference and strategic request actions, demonstrating robust performance across varying qualities and adaptation to changing reliability.
Autonomous agents operating in sequential decision-making tasks under uncertainty can benefit from external action suggestions, which provide valuable guidance but inherently vary in reliability. Existing methods for incorporating such advice typically assume static and known suggester quality parameters, limiting practical deployment. We introduce a framework that dynamically learns and adapts to varying suggester reliability in partially observable environments. First, we integrate suggester quality directly into the agent's belief representation, enabling agents to infer and adjust their reliance on suggestions through Bayesian inference over suggester types. Second, we introduce an explicit ``ask'' action allowing agents to strategically request suggestions at critical moments, balancing informational gains against acquisition costs. Experimental evaluation demonstrates robust performance across varying suggester qualities, adaptation to changing reliability, and strategic management of suggestion requests. This work provides a foundation for adaptive human-agent collaboration by addressing suggestion uncertainty in uncertain environments.