340 search results - page 56 / 68 » Kernelized value function approximation for reinforcement le... |
209
Voted
BDA
2007
15 years 3 months ago
2007
In content-based retrieval, relevance feedback (RF) is a noticeable method for reducing the “semantic gap” between the low-level features describing the content and the usually...
116
Voted
ICML
1994
IEEE
15 years 6 months ago
1994
IEEE
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
126
click to vote
AAAI
2011
14 years 2 months ago
2011
In this paper we propose differential eligibility vectors (DEV) for temporal-difference (TD) learning, a new class of eligibility vectors designed to bring out the contribution of...
92
Voted
NIPS
2003
15 years 3 months ago
2003
We study an approach to policy selection for large relational Markov Decision Processes (MDPs). We consider a variant of approximate policy iteration (API) that replaces the usual...
123
Voted
NIPS
1998
15 years 3 months ago
1998
In this paper, we address two issues of long-standing interest in the reinforcement learning literature. First, what kinds of performance guarantees can be made for Q-learning aft...