Integrating cognitive map learning and active inference for planning in ambiguous environments
This work addresses the challenge of robust planning under uncertainty for autonomous agents or AI systems, representing an incremental advance by combining existing models in a novel way.
The paper tackled the problem of integrating cognitive map learning with planning mechanisms for navigation in ambiguous environments, proposing a method that combines a cognitive map model with active inference and showing that the active inference agent outperforms a naive agent in challenging scenarios with ambiguous sensory information.
Living organisms need to acquire both cognitive maps for learning the structure of the world and planning mechanisms able to deal with the challenges of navigating ambiguous environments. Although significant progress has been made in each of these areas independently, the best way to integrate them is an open research question. In this paper, we propose the integration of a statistical model of cognitive map formation within an active inference agent that supports planning under uncertainty. Specifically, we examine the clone-structured cognitive graph (CSCG) model of cognitive map formation and compare a naive clone graph agent with an active inference-driven clone graph agent, in three spatial navigation scenarios. Our findings demonstrate that while both agents are effective in simple scenarios, the active inference agent is more effective when planning in challenging scenarios, in which sensory observations provide ambiguous information about location.