[A3L-D] Nonlinear Dynamics of Neuromorphic Computing and Hardware Implementation II

[A3L-D-03] Online Reinforcement Learning on Reservoir Based Actor-Critic Model with Gibbs’s Policy

*Tatsuro Nagai¹, Yuichi Katori¹ (1. Future University Hakodate)

Keywords:ESN, Actor-Critic algorithm, reinforcement learning, POMDP