Free online reference management for clinicians and scientists
Recent "reinforcement" articles
- These articles and links have been posted by Connotea users using the tag "reinforcement".
- To add to this collection, or to start your own library:
Watch a short video (2m 41s)
Create a Connotea Community Page about this tag. 

Number of articles per page:
Journal of basic and clinical physiology and pharmacology 11 (4), 305-20 (2000)
Neural networks : the official journal of the International Neural Network Society 15 (4-6), 535-47
Brain research 1153, 111-21 (11 Jun 2007)
Proceedings of the National Academy of Sciences of the United States of America 104 (22), 9493-8 (29 May 2007)
Science 318 (5854), 1309-12 (23 Nov 2007)
Journal of addictive diseases : the official journal of the ASAM, American Society of Addiction Medicine 17 (4), 33-48 (1998)
Annals of the New York Academy of Sciences 937, 1-26 (Jun 2001)
Life sciences 55 (17), L339-44 (1994)
The effects of delta-receptor antagonists on cocaine- and methamphetamine-induced place preferences were examined in rats. Cocaine- and methamphetamine-induced place preferences were significantly attenuated by naltrindole (NTI: a non-selective delta-opioid receptor antagonist). Furthermore, naltriben (NTB: a selective delta 2-opioid receptor antagonist), but not 7-benzylidenenaltrexone (BNTX: a selective delta 1-opioid receptor antagonist), attenuated the cocaine- and methamphetamine-induced place preferences. These results suggest that delta-opioid receptors, particularly delta 2-opioid receptors, may be involved in the reinforcing effects of cocaine and methamphetamine.
Artificial Intelligence 136 (2), 215 (2002)
Learning to act in a multiagent environment is a difficult problem since the normal definition of an optimal policy no longer applies. The optimal policy at any moment depends on the policies of the other agents. This creates a situation of learning a moving target. Previous learning algorithms have one of two shortcomings depending on their approach. They either converge to a policy that may not be optimal against the specific opponents' policies, or they may not converge at all. In this article we examine this learning problem in the framework of stochastic games. We look at a number of previous learning algorithms showing how they fail at one of the above criteria. We then contribute a new reinforcement learning technique using a variable learning rate to overcome these shortcomings. Specifically, we introduce the WoLF principle, “Win or Learn Fast”, for varying the learning rate. We examine this technique theoretically, proving convergence in self-play on a restricted class of iterated matrix games. We also present empirical results on a variety of more general stochastic games, in situations of self-play and otherwise, demonstrating the wide applicability of this method.
Author Keywords: Multiagent learning; Reinforcement learning; Game theory
<< Prev 0 Showing entries 1 to 10 of 36 total Next 10 >>


