Search Sciweavers | Sciweavers

15

ML
2008
ACM

152views Machine Learning» more ML 2008»

Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path

13 years 4 months ago

Download hal.inria.fr

Abstract. We consider batch reinforcement learning problems in continuous space, expected total discounted-reward Markovian Decision Problems. As opposed to previous theoretical wo...

András Antos, Csaba Szepesvári, R&ea...

claim paper

Read More »

14

click to vote

NIPS
2003

196views Information Technology» more NIPS 2003»

Approximate Policy Iteration with a Policy Language Bias

13 years 5 months ago

Download www.jair.org

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...

Alan Fern, Sung Wook Yoon, Robert Givan

claim paper

Read More »

18

click to vote

IJCAI
2003

147views Artificial Intelligence» more IJCAI 2003»

Approximate Policy Iteration using Large-Margin Classifiers

13 years 5 months ago

Download ijcai.org

We present an approximate policy iteration algorithm that uses rollouts to estimate the value of each action under a given policy in a subset of states and a classifier to general...

Michail G. Lagoudakis, Ronald Parr

claim paper

Read More »

16

click to vote

NN
2010
Springer

187views Neural Networks» more NN 2010»

Efficient exploration through active learning for value function approximation in reinforcement learning

12 years 11 months ago

Download sugiyama-www.cs.titech.ac.jp

Appropriately designing sampling policies is highly important for obtaining better control policies in reinforcement learning. In this paper, we first show that the least-squares ...

Takayuki Akiyama, Hirotaka Hachiya, Masashi Sugiya...

claim paper

Read More »

11

click to vote

ICML
2003
IEEE

174views Machine Learning» more ICML 2003»

Error Bounds for Approximate Policy Iteration

14 years 5 months ago