Propagating learned behaviors from a virtual agent to a physical robot in reinforcement learning

Proceedings of the IEEE Conference on Evolutionary Computation

Volumn , Issue , 1996, Pages 855-860

  Yamaguchi, Tomohiro ^a   Masubuchi, Motohmi ^a   Tanaka, Yasuhiro ^a   Yachida, Masahiko ^a  

^a OSAKA UNIVERSITY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL COMPLEXITY; COMPUTER SIMULATION; CONVERGENCE OF NUMERICAL METHODS; ERRORS; LEARNING SYSTEMS;

EXPLORATION ORIENTED METHODS; HIGH SPEED LEARNING METHOD; PHYSICAL ROBOT; REINFORCEMENT LEARNING; VIRTUAL LEARNING;

ROBOTS;

EID: 0029702801     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (0)