TY - GEN
T1 - Intrinsically motivated information foraging
AU - Fasel, Ian
AU - Wilt, Andrew
AU - Mafi, Nassim
AU - Morrison, Clayton T.
PY - 2010
Y1 - 2010
N2 - We treat information gathering as a POMDP in which the goal is to maximize an accumulated intrinsic reward at each time step based on the negative entropy of the agent's beliefs about the world state. We show that such information foraging agents can discover intelligent exploration policies that take into account the long-term effects of sensor and motor actions, and can automatically adapt to variations in sensor noise, different amounts of prior information, and limited memory conditions.
AB - We treat information gathering as a POMDP in which the goal is to maximize an accumulated intrinsic reward at each time step based on the negative entropy of the agent's beliefs about the world state. We show that such information foraging agents can discover intelligent exploration policies that take into account the long-term effects of sensor and motor actions, and can automatically adapt to variations in sensor noise, different amounts of prior information, and limited memory conditions.
UR - http://www.scopus.com/inward/record.url?scp=78149267893&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78149267893&partnerID=8YFLogxK
U2 - 10.1109/DEVLRN.2010.5578859
DO - 10.1109/DEVLRN.2010.5578859
M3 - Conference contribution
AN - SCOPUS:78149267893
SN - 9781424469024
T3 - 2010 IEEE 9th International Conference on Development and Learning, ICDL-2010 - Conference Program
SP - 101
EP - 107
BT - 2010 IEEE 9th International Conference on Development and Learning, ICDL-2010 - Conference Program
T2 - 2010 IEEE 9th International Conference on Development and Learning, ICDL-2010
Y2 - 18 August 2010 through 21 August 2010
ER -