TY - GEN
T1 - Learning similar tasks from observation and practice
AU - Bentivegna, Darrin C.
AU - Atkeson, Christopher G.
AU - Cheng, Gordon
PY - 2006
Y1 - 2006
N2 - This paper presents a case study of learning to select behavioral primitives and generate subgoals from observation and practice. Our approach uses local features to generalize across tasks and global features to learn from practice. We demonstrate this approach applied to the marble maze task. Our robot uses local features to initially learn primitive selection and subgoal generation policies from observing a teacher maneuver a marble through a maze. The robot then uses this information as it tries to traverse another maze, and refines the information during learning from practice.
AB - This paper presents a case study of learning to select behavioral primitives and generate subgoals from observation and practice. Our approach uses local features to generalize across tasks and global features to learn from practice. We demonstrate this approach applied to the marble maze task. Our robot uses local features to initially learn primitive selection and subgoal generation policies from observing a teacher maneuver a marble through a maze. The robot then uses this information as it tries to traverse another maze, and refines the information during learning from practice.
UR - http://www.scopus.com/inward/record.url?scp=34250635403&partnerID=8YFLogxK
U2 - 10.1109/IROS.2006.281989
DO - 10.1109/IROS.2006.281989
M3 - Conference contribution
AN - SCOPUS:34250635403
SN - 142440259X
SN - 9781424402595
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 2677
EP - 2683
BT - 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006
T2 - 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006
Y2 - 9 October 2006 through 15 October 2006
ER -