Successor Representation Active Inference
This work addresses the challenge of improving active inference agents for AI researchers by offering a more efficient alternative, though it appears incremental as it builds on existing concepts.
The paper tackled the problem of linking the successor representation in reinforcement learning to Bayesian filtering, resulting in a novel active inference agent architecture that shows advantages in planning horizon and computational cost over current agents.
Recent work has uncovered close links between between classical reinforcement learning algorithms, Bayesian filtering, and Active Inference which lets us understand value functions in terms of Bayesian posteriors. An alternative, but less explored, model-free RL algorithm is the successor representation, which expresses the value function in terms of a successor matrix of expected future state occupancies. In this paper, we derive the probabilistic interpretation of the successor representation in terms of Bayesian filtering and thus design a novel active inference agent architecture utilizing successor representations instead of model-based planning. We demonstrate that active inference successor representations have significant advantages over current active inference agents in terms of planning horizon and computational cost. Moreover, we demonstrate how the successor representation agent can generalize to changing reward functions such as variants of the expected free energy.