Smoothed Sarsa: Reinforcement learning for robot delivery tasks
作者： Deepak Ramachandran , Rakesh Gupta
DOI: 10.1109/ROBOT.2009.5152707
关键词:
摘要: … reinforcement learning algorithm called Smoothed Sarsa that learns a good policy for these delivery tasks by delaying the backup reinforcement … Smoothed Sarsa learns a policy orders …
lens.org 参考文章(38)
Arnaud Doucet, Neil J. Gordon, Joao F. G. De Freitas, Editors: Sequential Monte Carlo Methods in Practice ,(2001)
Sven Koenig, Reid Simmons, Probabilistic robot navigation in partially observable environments international joint conference on artificial intelligence. pp. 1080- 1087 ,(1995)
Eva Andreasson, System and method for reinforcement learning and memory management ,(2003)
Mukesh Dalal, Armand Prieditis, Optimizing active decision making using simulated decision making ,(2004)
Hiroshi Tsujino, Johane Takeuchi, Learning system and learning method ,(2009)
Sequential Monte Carlo methods in practice Springer. ,(2001) , 10.1007/978-1-4757-3437-9
Damien Ernst, Arthur Louette, Introduction to Reinforcement Learning MIT Press. ,(1998)
Kohtaro Sabe, Kenichi Hidai, Learning control apparatus, learning control method, and computer program ,(2006)
S. Schaal, J. Peters, Sethu Vijayakumar, Reinforcement Learning for Humanoid Robotics ieee ras international conference on humanoid robots. pp. 1- 20 ,(2003)