TY - GEN
T1 - Risk-averse sensor planning using distributed policy gradient
AU - Ma, Wann Jiun
AU - Dentcheva, Darinka
AU - Zavlanos, Michael M.
N1 - Publisher Copyright:
© 2017 American Automatic Control Council (AACC).
PY - 2017/6/29
Y1 - 2017/6/29
N2 - This paper considers a risk-averse approach to planning the motion of mobile sensor networks in order to maximize the information they collect in uncertain environments. Recent models of risk shape the tails of the probability distributions of the decision variables, controlling in this way the occurrence of rare but important events. In this paper, we formulate the sensor planning problem as a Markov Decision Process (MDP) and propose a distributed risk-averse policy gradient method to obtain optimal policies for the team of sensors. These policies avoid extremely low reward and high risk events. The simulation results validate the effectiveness of the proposed distributed risk-averse method.
AB - This paper considers a risk-averse approach to planning the motion of mobile sensor networks in order to maximize the information they collect in uncertain environments. Recent models of risk shape the tails of the probability distributions of the decision variables, controlling in this way the occurrence of rare but important events. In this paper, we formulate the sensor planning problem as a Markov Decision Process (MDP) and propose a distributed risk-averse policy gradient method to obtain optimal policies for the team of sensors. These policies avoid extremely low reward and high risk events. The simulation results validate the effectiveness of the proposed distributed risk-averse method.
UR - http://www.scopus.com/inward/record.url?scp=85027001784&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85027001784&partnerID=8YFLogxK
U2 - 10.23919/ACC.2017.7963704
DO - 10.23919/ACC.2017.7963704
M3 - Conference contribution
AN - SCOPUS:85027001784
T3 - Proceedings of the American Control Conference
SP - 4839
EP - 4844
BT - 2017 American Control Conference, ACC 2017
T2 - 2017 American Control Conference, ACC 2017
Y2 - 24 May 2017 through 26 May 2017
ER -