时序差分学习算法TD().PPT

* * * * * * * * * * * * * * * * * * * * * * * * Observations: {laser, speech, touchscreen, reminder} State features: robot_location person_location person_status reminder_goal motion_goal user_goal * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * 史忠植 强化学习 * Nursing Robot Pearl 史忠植 强化学习 Pearl介绍 Pearl is a prototype nursing robot, providing assistance to both nurses and elderly people. “thinkers” eyes with cameras sonar sensors handlebars wheeled base carrying tray LCD smile/frown * * CogRob2002 workshop 史忠植 强化学习 老年人数 450,000 more nurses needed by 2008 campaign to recruit and retain nurses  and other health care providers * * 史忠植 强化学习 Moving things around Enabling use of remote health services Supporting inter-personal communication Calling for help in emergencies Monitoring Rx adherence safety Providing information (TV, weather) Management support of ADLs Reminding to eat, drink, take meds Providing physical assistance Linking the caregiver to resources 机器人助理保健 * * * 史忠植 强化学习 * References Sutton, R.S. and Barto, A.G. (1998). Reinforcement Learning- An Introduction. Hastie, T., Tibshirani, R. and Friedman, J. (2001). The Elements of Statistical Learning-Data Mining, Inference and Prediction. Murphy, S.A. (2003). Optimal Dynamic Treatment Regimes. JRSS-B. Blatt, D., Murphy, S.A. and Zhu, J. (2004). A-Learning for Approximate Planning. Murphy, S.A. (2004). A Generalization Error for Q-Learning. D. P. Bertsekas and J. N. Tsitsiklis (1996). Neuro-Dynamic Programming. 宋志伟, 陈小平, 2003. 仿真机器人足球中的强化学习. 《机器人》, 24(7S):761-766. Joelle Pineau and Sebastian Thrun. High-level robot behavior control using POMDPs. CogRob2002 workshop. * 史忠植 强化学习 * Thank You Intelligence Science / * * * * * * * * * * * * * * * * * * * * * * * * * * * 史忠植 强化学习 * POMDP部分感知马氏决策过程 Rather than observing the state we observe some function of the state. Ob – Observable function a random variable for each