102
Voted
ML
2008
ACM
14 years 9 months ago
2008
ACM
Abstract. We consider batch reinforcement learning problems in continuous space, expected total discounted-reward Markovian Decision Problems. As opposed to previous theoretical wo...
65
Voted
COLT
2000
Springer
15 years 1 months ago
2000
Springer
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process ( ¢¡¤£¦¥§ ), and focus on gradient ascent approache...
95
Voted
CDC
2009
IEEE
15 years 2 months ago
2009
IEEE
— This paper addresses model reduction for a Markov chain on a large state space. A simulation-based framework is introduced to perform state aggregation of the Markov chain base...
68
Voted
ICML
2000
IEEE
15 years 10 months ago
2000
IEEE
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...