Sciweavers

226 search results - page 9 / 46
» A Convergent Reinforcement Learning Algorithm in the Continu...
Sort
View
IROS
2009
IEEE
206views Robotics» more  IROS 2009»
14 years 1 months ago
Bayesian reinforcement learning in continuous POMDPs with gaussian processes
— Partially Observable Markov Decision Processes (POMDPs) provide a rich mathematical model to handle realworld sequential decision processes but require a known model to be solv...
Patrick Dallaire, Camille Besse, Stéphane R...
EUROCAST
2007
Springer
182views Hardware» more  EUROCAST 2007»
14 years 26 days ago
A k-NN Based Perception Scheme for Reinforcement Learning
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
José Antonio Martin H., Javier de Lope Asia...
NIPS
2007
13 years 8 months ago
Reinforcement Learning in Continuous Action Spaces through Sequential Monte Carlo Methods
Learning in real-world domains often requires to deal with continuous state and action spaces. Although many solutions have been proposed to apply Reinforcement Learning algorithm...
Alessandro Lazaric, Marcello Restelli, Andrea Bona...
COLT
2000
Springer
13 years 11 months ago
Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process (  ¢¡¤£¦¥§  ), and focus on gradient ascent approache...
Peter L. Bartlett, Jonathan Baxter
ECML
2007
Springer
13 years 10 months ago
Efficient Continuous-Time Reinforcement Learning with Adaptive State Graphs
Abstract. We present a new reinforcement learning approach for deterministic continuous control problems in environments with unknown, arbitrary reward functions. The difficulty of...
Gerhard Neumann, Michael Pfeiffer, Wolfgang Maass