This paper describes the adaption and application of an algorithm called Feudal Reinforcement Learning to a complex gridworld navigation problem. The algorithm proved to be not ea...
Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning domains that require balancing actions that increase an agent's knowledge and actions that ...
In this paper we investigate the relation between transfer learning in reinforcement learning with function approximation and supervised learning with concept drift. We present a n...
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of ...
— We have found a more general formulation of the REINFORCE learning principle which had been proposed by R. J. Williams for the case of artificial neural networks with stochast...