Sciweavers

664 search results - page 5 / 133
» Combining Reinforcement Learning with a Local Control Algori...
Sort
View
SMC
2007
IEEE
102views Control Systems» more  SMC 2007»
15 years 4 months ago
An improved immune Q-learning algorithm
—Reinforcement learning is a framework in which an agent can learn behavior without knowledge on a task or an environment by exploration and exploitation. Striking a balance betw...
Zhengqiao Ji, Q. M. Jonathan Wu, Maher A. Sid-Ahme...
ICML
2000
IEEE
15 years 10 months ago
Reinforcement Learning in POMDP's via Direct Gradient Ascent
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...
Jonathan Baxter, Peter L. Bartlett
AR
2007
105views more  AR 2007»
14 years 10 months ago
Reinforcement learning of a continuous motor sequence with hidden states
—Reinforcement learning is the scheme for unsupervised learning in which robots are expected to acquire behavior skills through self-explorations based on reward signals. There a...
Hiroaki Arie, Tetsuya Ogata, Jun Tani, Shigeki Sug...
ICML
2007
IEEE
15 years 10 months ago
Reinforcement learning by reward-weighted regression for operational space control
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of ...
Jan Peters, Stefan Schaal
ATAL
2010
Springer
14 years 11 months ago
Combining manual feedback with subsequent MDP reward signals for reinforcement learning
As learning agents move from research labs to the real world, it is increasingly important that human users, including those without programming skills, be able to teach agents de...
W. Bradley Knox, Peter Stone