A typical goal for transfer learning algorithms is to utilize knowledge gained in a source task to learn a target task faster. Recently introduced transfer methods in reinforcemen...
lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...
We empirically evaluate the performance of various reinforcement learning methods in applications to sequential targeted marketing. In particular, we propose and evaluate a progre...
Naoki Abe, Edwin P. D. Pednault, Haixun Wang, Bian...
Recently researchers have introduced methods to develop reusable knowledge in reinforcement learning (RL). In this paper, we define simple principles to combine skills in reinforce...
We present a new subgoal-based method for automatically creating useful skills in reinforcement learning. Our method identifies subgoals by partitioning local state transition gra...