TOMACS
2010
12 years 11 months ago
2010
In this paper, we develop a stochastic approximation method to solve a monotone estimation problem and use this method to enhance the empirical performance of the Q-learning algor...
JMLR
2010
12 years 11 months ago
2010
We consider the Bellman residual minimization approach for solving discounted Markov decision problems, where we assume that a generative model of the dynamics and rewards is avai...
ICMLA
2009
13 years 2 months ago
2009
We describe a system that successfully transfers value function knowledge across multiple subdomains of realtime strategy games in the context of multiagent reinforcement learning....
ICRA
2010
IEEE
13 years 3 months ago
2010
IEEE
— We consider the problem of task assignment and execution in multirobot systems, by proposing a procedure for bid estimation in auction protocols. Auctions are of interest to mu...
MP
2006
13 years 4 months ago
2006
We consider two-stage pure integer programs with discretely distributed stochastic right-hand sides. We present an equivalent superadditive dual formulation that uses the value fun...
AI
2008
Springer
13 years 4 months ago
2008
Springer
Classical work on eliciting and representing preferences over multi-attribute alternatives has attempted to recognize conditions under which value functions take on particularly s...
ICML
2010
IEEE
13 years 5 months ago
2010
IEEE
We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorit...
NIPS
2000
13 years 5 months ago
2000
We propose a method of approximate dynamic programming for Markov decision processes (MDPs) using algebraic decision diagrams (ADDs). We produce near-optimal value functions and p...
DAGSTUHL
2008
13 years 6 months ago
2008
Abstract. In this chapter, we present a new interactive procedure for multiobjective optimization, which is based on the use of a set of value functions as a preference model built...
GECCO
2010
Springer
13 years 7 months ago
2010
Springer
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, rese...