Bayesian Inference of Self-intention Attributed by Observer
This addresses the challenge of human-agent collaboration in RL by enabling agents to infer human-attributed mental states, though it is incremental as it builds on existing mental state inference concepts.
The paper tackles the problem of RL agents lacking communication abilities for human collaboration by proposing the PublicSelf model, which infers the mental states people attribute to the agent; results showed the model correctly inferred attributed intentions in scenes where people perceived intentionality from the agent's behavior.
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.