On the Difficulty of Modular Reinforcement Learning for Real-World Partial Programming
暂无分享,去创建一个
[1] K. Arrow,et al. Social Choice and Individual Values , 1951 .
[2] Thomas G. Dietterich. The MAXQ Method for Hierarchical Reinforcement Learning , 1998, ICML.
[3] David Andre,et al. Programmable Reinforcement Learning Agents , 2000, NIPS.
[4] Jonas Karlsson,et al. Learning to Solve Multiple Goals , 1997 .
[5] Maja J. Matarić,et al. Action Selection methods using Reinforcement Learning , 1996 .
[6] Kevin Roberts,et al. Interpersonal Comparability and Social Choice Theory , 1980 .
[7] Andrew Stern,et al. A Behavior Language for Story-Based Believable Agents , 2002, IEEE Intell. Syst..
[8] A. B. Loyall,et al. Integrating Reactivity, Goals, and Emotion in a Broad Agent , 1992 .
[9] Jon Doyle,et al. Impediments to Universal Preference-Based Default Theories , 1989, KR.
[10] Dana H. Ballard,et al. Multiple-Goal Reinforcement Learning with Modular Sarsa(0) , 2003, IJCAI.
[11] Stuart J. Russell,et al. Q-Decomposition for Reinforcement Learning Agents , 2003, ICML.
[12] P. Reny. Arrow’s theorem and the Gibbard-Satterthwaite theorem: a unified approach , 2001 .