Autonomous reinforcement of behavioral sequences in neural dynamics

†Joint first authors. Abstract — We introduce a dynamic neural algorithm called Dynamic Neural (DN) SARSA(λ) for learning a behavioral se-quence from delayed reward. DN-SARSA(λ) combines Dynamic Field Theory models of behavioral sequence representation, classical reinforcement learning, and a computational neuro-science model of working memory, called Item and Order work-ing memory, which serves as an eligibility trace. DN-SARSA(λ) is implemented on both a simulated and real robot that must learn a specific rewarding sequence of elementary behaviors from exploration. Results show DN-SARSA(λ) performs on the level of the discrete SARSA(λ), validating the feasibility of general reinforcement learning without compromising neural dynamics. I