— Libraries of trajectories are a promising way of creating policies for difficult problems. However, often it is not desirable or even possible to create a new library for ever...
Martin Stolle, Hanns Tappeiner, Joel E. Chestnutt,...
— We present a control approach that uses a library of trajectories to establish a global control law or policy. This is an alternative to methods for finding global policies ba...
Bayesian inference is an appealing approach for leveraging prior knowledge in reinforcement learning (RL). In this paper we describe an algorithm for discovering different classes...
This work represents the first step towards a task library system in the reinforcement learning domain. Task libraries could be useful in speeding up the learning of new tasks th...
James L. Carroll, Todd S. Peterson, Kevin D. Seppi
Abstract— We consider the problem of apprenticeship learning when the expert’s demonstration covers only a small part of a large state space. Inverse Reinforcement Learning (IR...