Collaborative Decision Making Using Action Suggestions
This work addresses failure mitigation in autonomous systems by enhancing human oversight through efficient suggestion-based collaboration, representing an incremental improvement in human-AI interaction methods.
The authors tackled the problem of autonomous system failures by proposing a collaborative decision-making method using action suggestions, which improved action selection without taking control and achieved better performance with fewer suggestions than naive approaches, as demonstrated through simulated experiments.
The level of autonomy is increasing in systems spanning multiple domains, but these systems still experience failures. One way to mitigate the risk of failures is to integrate human oversight of the autonomous systems and rely on the human to take control when the autonomy fails. In this work, we formulate a method of collaborative decision making through action suggestions that improves action selection without taking control of the system. Our approach uses each suggestion efficiently by incorporating the implicit information shared through suggestions to modify the agent's belief and achieves better performance with fewer suggestions than naively following the suggested actions. We assume collaborative agents share the same objective and communicate through valid actions. By assuming the suggested action is dependent only on the state, we can incorporate the suggested action as an independent observation of the environment. The assumption of a collaborative environment enables us to use the agent's policy to estimate the distribution over action suggestions. We propose two methods that use suggested actions and demonstrate the approach through simulated experiments. The proposed methodology results in increased performance while also being robust to suboptimal suggestions.