31 search results - page 1 / 7 » Algorithms and Bounds for Rollout Sampling Approximate Polic... |
Publication
Abstract: Several approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervis...
Publication
Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schem...
IJCAI
2003
13 years 5 months ago
2003
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...
ML
2008
ACM
13 years 4 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...
NIPS
2003
13 years 5 months ago
2003
We describe a new approximation algorithm for solving partially observable MDPs. Our bounded policy iteration approach searches through the space of bounded-size, stochastic fini...