A reinforcement learning approach to fail-safe design for multiple space robots--cooperation mechanism without communication and negotiation schemes.

Keiki Takadama Shuichi Matsumoto Shinichi Nakasuka Katsunori Shimohara A reinforcement learning approach to fail-safe design for multiple space robots--cooperation mechanism without communication and negotiation schemes. 21-39 2003 17 Advanced Robotics 1 http://dx.doi.org/10.1163/156855303321125604 db/journals/ar/ar17.html#TakadamaMNS03