- The effectiveness of stochastic power management relies on the accurate system and workload model and effective policy optimization. Workload modeling is a machine learning proce...
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...
— This paper presents an algorithm for adapting periodic behavior to gradual shifts in task parameters. Since learning optimal control in high dimensional domains is subject to t...
Privacy is a concept which received relatively little attention during the rapid growth and spread of information technology through the 1980’s and 1990’s. Design to make info...
Carolyn Brodie, Clare-Marie Karat, John Karat, Jin...
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
Shalabh Bhatnagar, Richard S. Sutton, Mohammad Gha...