Hierarchical memory-based reinforcement learning Export

@inproceedings{citeulike:3926349, abstract = {A key challenge for reinforcement learning is scaling up to large partially observable domains. In this paper, we show how a hierarchy of behaviors can be used to create and select among variable length short-term memories appropriate for a task. At higher levels in the hierarchy, the agent abstracts over lower-level details and looks back over a variable number of high-level decisions in time. We formalize this idea in a framework called Hierarchical Sux Memory (HSM). HSM uses a memory-based SMDP learning method to rapidly propagate delayed reward across long decision sequences. We describe a detailed experimental study comparing memory vs. hierarchy using the HSM framework on a realistic corridor navigation task. 1}, author = {Hernandez-Gardiol, Natalia and Mahadevan, Sridhar}, booktitle = {In Advances in Neural Information Processing Systems (NIPS}, citeulike-article-id = {3926349}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32.7258}, keywords = {ml}, pages = {1047--1053}, posted-at = {2009-01-23 03:31:15}, priority = {2}, title = {Hierarchical memory-based reinforcement learning}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32.7258}, volume = {13}, year = {2001} }

TY - CONF ID - citeulike:3926349 L3 - citeulike-article-id:3926349 N2 - A key challenge for reinforcement learning is scaling up to large partially observable domains. In this paper, we show how a hierarchy of behaviors can be used to create and select among variable length short-term memories appropriate for a task. At higher levels in the hierarchy, the agent abstracts over lower-level details and looks back over a variable number of high-level decisions in time. We formalize this idea in a framework called Hierarchical Sux Memory (HSM). HSM uses a memory-based SMDP learning method to rapidly propagate delayed reward across long decision sequences. We describe a detailed experimental study comparing memory vs. hierarchy using the HSM framework on a realistic corridor navigation task. 1 EP - 1053 TI - Hierarchical memory-based reinforcement learning VL - 13 T2 - In Advances in Neural Information Processing Systems (NIPS SP - 1047 KW - ml AU - Hernandez-Gardiol, Natalia AU - Mahadevan, Sridhar PY - 2001/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32.7258 ER -