We present a new algorithm, GM-Sarsa(0), for finding approximate solutions to multiple-goal reinforcement learning problems that are modeled as composite Markov decision processe...
Markov Decision Processes (MDPs) have been extensively studied and used in the context of planning and decision-making, and many methods exist to find the optimal policy for probl...
Abstract— We propose to improve the locomotive performance of humanoid robots by using approximated biped stepping and walking dynamics with reinforcement learning (RL). Although...
Jun Morimoto, Christopher G. Atkeson, Gen Endo, Go...
In combinatorial solution spaces Iterated Local Search (ILS) turns out to be exceptionally successful. The question arises: is ILS also capable of improving the optimization proces...
Selecting an optimum maintenance policy independent of other parameters of the production system does not always yield the overall optimum operating conditions. For instance, high...