Generalization and Scaling in Reinforcement Learning

@inproceedings{citeulike:2924870, abstract = {In associative reinforcement learning, an environment generates input vectors, a learning system generates possible output vectors, and a reinforcement function computes feedback signals from the input-output pairs. The task is to discover and remember input-output pairs that generate rewards. Especially difficult cases occur when rewards are rare, since the expected time for any algorithm can grow exponentially with the size of the problem. Nonetheless, if a reinforcement function possesses...}, address = {Denver 1989}, author = {Ackley, D. H. and Littman, M. S. }, booktitle = {Advances in Neural Information Processing Systems}, citeulike-article-id = {2924870}, editor = {Touretzky, D. S. }, keywords = {learning}, pages = {550--557}, posted-at = {2008-06-25 02:46:23}, priority = {2}, publisher = {Morgan Kaufmann, San Mateo}, title = {Generalization and Scaling in Reinforcement Learning}, url = {http://citeseer.ist.psu.edu/ackley90generalization.html}, volume = {2}, year = {1990} }

TY - CONF ID - citeulike:2924870 L3 - citeulike-article-id:2924870 TI - Generalization and Scaling in Reinforcement Learning T2 - Advances in Neural Information Processing Systems VL - 2 SP - 550 EP - 557 AD - Denver 1989 PB - Morgan Kaufmann, San Mateo N2 - In associative reinforcement learning, an environment generates input vectors, a learning system generates possible output vectors, and a reinforcement function computes feedback signals from the input-output pairs. The task is to discover and remember input-output pairs that generate rewards. Especially difficult cases occur when rewards are rare, since the expected time for any algorithm can grow exponentially with the size of the problem. Nonetheless, if a reinforcement function possesses... KW - learning AU - Ackley, DH AU - Littman, MS A2 - Touretzky, DS PY - 1990/// UR - http://citeseer.ist.psu.edu/ackley90generalization.html ER -