Bayesian Inference of Self-intention Attributed by Observer

TL;DR

This paper introduces the PublicSelf model, enabling reinforcement learning agents to infer how their behavior appears to others, thereby improving human-agent interaction by understanding perceived intentions.

Contribution

The paper presents the PublicSelf model, a novel approach for RL agents to infer human-attributed mental states based on their own behavior in simulated environments.

Findings

The model accurately inferred perceived intentions in scenes with identifiable intentionality.

The agent's inferred mental states aligned with human judgments in the simulation.

The approach enhances understanding of agent behavior from a human perspective.

Abstract

Most of agents that learn policy for tasks with reinforcement learning (RL) lack the ability to communicate with people, which makes human-agent collaboration challenging. We believe that, in order for RL agents to comprehend utterances from human colleagues, RL agents must infer the mental states that people attribute to them because people sometimes infer an interlocutor's mental states and communicate on the basis of this mental inference. This paper proposes PublicSelf model, which is a model of a person who infers how the person's own behavior appears to their colleagues. We implemented the PublicSelf model for an RL agent in a simulated environment and examined the inference of the model by comparing it with people's judgment. The results showed that the agent's intention that people attributed to the agent's movement was correctly inferred by the model in scenes where people could find certain intentionality from the agent's behavior.