343 search results - page 35 / 69 » Action discovery for reinforcement learning |
NN
2007
Springer
13 years 7 months ago
2007
Springer
Reinforcement learning is based on exploration of the environment and receiving reward that indicates which actions taken by the agent are good and which ones are bad. In many app...
SOCROB
2010
2010
Using the Interaction Rhythm as a Natural Reinforcement Signal for Social Robots: A Matter of Belief
13 years 6 months ago
Abstract. In this paper, we present the results of a pilot study of a human robot interaction experiment where the rhythm of the interaction is used as a reinforcement signal to le...
RAS
2010
13 years 6 months ago
2010
Policy Reuse is a reinforcement learning technique that efficiently learns a new policy by using past similar learned policies. The Policy Reuse learner improves its exploration b...
ICML
2005
IEEE
14 years 8 months ago
2005
IEEE
We prove a quantitative connection between the expected sum of rewards of a policy and binary classification performance on created subproblems. This connection holds without any ...
ESANN
2008
13 years 9 months ago
2008
The aim of this paper is to enhance the performance of a reinforcement learning game agent controller, within a dynamic game environment, through the retention of learned informati...