TY - GEN
T1 - Concurrent probabilistic temporal planning with policy-gradients
AU - Aberdeen, Douglas
AU - Buffet, Olivier
PY - 2007
Y1 - 2007
N2 - We present an any-time concurrent probabilistic temporal planner that includes continuous and discrete uncertainties and metric functions. Our approach is a direct policy search that attempts to optimise a parameterised policy using gradient ascent. Low memory use, plus the use of function approximation methods, plus factorisation of the policy, allow us to scale to challenging domains. This Factored Policy Gradient (FPG) Planner also attempts to optimise both steps to goal and the probability of success. We compare the FPG planner to other planners on CPTP domains, and on simpler but better studied probabilistic non-temporal domains.
AB - We present an any-time concurrent probabilistic temporal planner that includes continuous and discrete uncertainties and metric functions. Our approach is a direct policy search that attempts to optimise a parameterised policy using gradient ascent. Low memory use, plus the use of function approximation methods, plus factorisation of the policy, allow us to scale to challenging domains. This Factored Policy Gradient (FPG) Planner also attempts to optimise both steps to goal and the probability of success. We compare the FPG planner to other planners on CPTP domains, and on simpler but better studied probabilistic non-temporal domains.
UR - http://www.scopus.com/inward/record.url?scp=58349090838&partnerID=8YFLogxK
M3 - Conference contribution
SN - 9781577353447
T3 - ICAPS 2007, 17th International Conference on Automated Planning and Scheduling
SP - 10
EP - 17
BT - ICAPS 2007, 17th International Conference on Automated Planning and Scheduling
PB - Association for the Advancement of Artificial Intelligence, AAAI
T2 - ICAPS 2007, 17th International Conference on Automated Planning and Scheduling
Y2 - 22 September 2007 through 26 September 2007
ER -