Recent advances in hierarchical reinforcement learning

@misc{citeulike:571875, abstract = {Reinforcement learning is bedeviled by the curse of dimensionality: the number of parameters to be learned grows exponentially with the size of any compact encoding of a state. Recent attempts to combat the curse of dimensionality have turned to principled ways of exploiting temporal abstraction, where decisions are not required at each step, but rather invoke the execution of temporally-extended activities which follow their own policies until termination. This leads naturally to hierarchical...}, author = {Barto, A. and Mahadevan, S. }, citeulike-article-id = {571875}, keywords = {hierarchical, learning, reinforcement}, posted-at = {2006-03-31 17:53:53}, priority = {4}, title = {Recent advances in hierarchical reinforcement learning}, url = {http://citeseer.ist.psu.edu/barto03recent.html}, year = {2003} }

TY - GEN ID - citeulike:571875 L3 - citeulike-article-id:571875 TI - Recent advances in hierarchical reinforcement learning N2 - Reinforcement learning is bedeviled by the curse of dimensionality: the number of parameters to be learned grows exponentially with the size of any compact encoding of a state. Recent attempts to combat the curse of dimensionality have turned to principled ways of exploiting temporal abstraction, where decisions are not required at each step, but rather invoke the execution of temporally-extended activities which follow their own policies until termination. This leads naturally to hierarchical... KW - hierarchical KW - learning KW - reinforcement AU - Barto, A AU - Mahadevan, S PY - 2003/// UR - http://citeseer.ist.psu.edu/barto03recent.html ER -