Reward-dependent sensory coding in free-energy-based reinforcement learning

The free-energy-based reinforcement learning is a new approach to handling high-dimensional states and actions. We investigate its properties using a new experimental platform called the digit floor task. In this task, the highdimensional pixel data of hand-written digits were directly used as sensory inputs to the reinforcement learning agent. The simulation results showed the robustness of the free-energy-based reinforcement learning method against noise applied in both the training and testing phases. In addition, reward-dependent sensory representations were found in the distributed activation patterns of hidden units. The representations coded in a distributed fashion persisted even when the number of hidden nodes were varied.