Autonomous Reinforcement of Behavioral Sequences in Neural Dynamics

no code implementations • 12 Oct 2012 • Sohrob Kazerounian, Matthew Luciw, Mathis Richter, Yulia Sandamirskaya

We introduce a dynamic neural algorithm called Dynamic Neural (DN) SARSA(\lambda) for learning a behavioral sequence from delayed reward.

General Reinforcement Learning reinforcement-learning +1