Efficient reinforcement learning: computational theories, neuroscience and robotics.

@article{citeulike:2805014, abstract = {Reinforcement learning algorithms have provided some of the most influential computational theories for behavioral learning that depends on reward and penalty. After briefly reviewing supporting experimental data, this paper tackles three difficult theoretical issues that remain to be explored. First, plain reinforcement learning is much too slow to be considered a plausible brain model. Second, although the temporal-difference error has an important role both in theory and in experiments, how to compute it remains an enigma. Third, function of all brain areas, including the cerebral cortex, cerebellum, brainstem and basal ganglia, seems to necessitate a new computational framework. Computational studies that emphasize meta-parameters, hierarchy, modularity and supervised learning to resolve these issues are reviewed here, together with the related experimental data.}, address = {ATR Computational Neuroscience Laboratories, 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan. kawato@atr.jp}, author = {Kawato, M. and Samejima, K. }, citeulike-article-id = {2805014}, doi = {http://dx.doi.org/10.1016/j.conb.2007.03.004}, issn = {0959-4388}, journal = {Current opinion in neurobiology}, keywords = {learning, reinforcement}, month = {April}, number = {2}, pages = {205--212}, posted-at = {2008-05-16 11:56:38}, priority = {5}, title = {Efficient reinforcement learning: computational theories, neuroscience and robotics.}, url = {http://dx.doi.org/10.1016/j.conb.2007.03.004}, volume = {17}, year = {2007} }

TY - JOUR ID - citeulike:2805014 L3 - citeulike-article-id:2805014 TI - Efficient reinforcement learning: computational theories, neuroscience and robotics. JF - Current opinion in neurobiology VL - 17 IS - 2 SP - 205 EP - 212 AD - ATR Computational Neuroscience Laboratories, 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan. kawato@atr.jp SN - 0959-4388 N2 - Reinforcement learning algorithms have provided some of the most influential computational theories for behavioral learning that depends on reward and penalty. After briefly reviewing supporting experimental data, this paper tackles three difficult theoretical issues that remain to be explored. First, plain reinforcement learning is much too slow to be considered a plausible brain model. Second, although the temporal-difference error has an important role both in theory and in experiments, how to compute it remains an enigma. Third, function of all brain areas, including the cerebral cortex, cerebellum, brainstem and basal ganglia, seems to necessitate a new computational framework. Computational studies that emphasize meta-parameters, hierarchy, modularity and supervised learning to resolve these issues are reviewed here, together with the related experimental data. KW - learning KW - reinforcement AU - Kawato, M AU - Samejima, K PY - 2007/04// UR - http://dx.doi.org/10.1016/j.conb.2007.03.004 ER -