Follow
Doug Aberdeen
Doug Aberdeen
Verified email at google.com
Title
Cited by
Cited by
Year
Policy-gradient algorithms for partially observable Markov decision processes
D Aberdeen
The Australian National University, 2003
1152003
The learning behind gmail priority inbox
D Aberdeen, O Pacovsky, A Slater
1092010
Decision-Theoretic Military Operations Planning.
D Aberdeen, S Thiébaux, L Zhang
ICAPS, 402-412, 2004
1092004
Scaling internal-state policy-gradient methods for POMDPs
D Aberdeen, J Baxter
MACHINE LEARNING-INTERNATIONAL WORKSHOP THEN CONFERENCE-, 3-10, 2002
1072002
Natural actor-critic for road traffic optimisation
S Richter, D Aberdeen, J Yu
Advances in neural information processing systems 19, 2006
1032006
A (revised) survey of approximate methods for solving partially observable Markov decision processes
D Aberdeen
Technical report, National ICT Australia, 2003
1012003
The factored policy-gradient planner
O Buffet, D Aberdeen
Artificial Intelligence 173 (5-6), 722-747, 2009
702009
Prottle: A probabilistic temporal planner
I Little, D Aberdeen, S Thiébaux
AAAI Press, 2005
692005
A survey of approximate methods for solving partially observable markov decision process
D Aberdeen
Report National ICT Australia, 2003
532003
Emmerald: a fast matrix–matrix multiply using Intel's SSE instructions
D Aberdeen, J Baxter
Concurrency and Computation: Practice and Experience 13 (2), 103-119, 2001
442001
Fast online policy gradient learning with SMD gain vector adaptation
J Yu, D Aberdeen, N Schraudolph
Advances in neural information processing systems 18, 2005
392005
Robust planning with (l) rtdp
O Buffet, D Aberdeen
IJCAI, 1214-1219, 2005
312005
Conditional random fields for multi-agent reinforcement learning
X Zhang, D Aberdeen, SVN Vishwanathan
Proceedings of the 24th international conference on Machine learning, 1143-1150, 2007
282007
FF+ FPG: Guiding a Policy-Gradient Planner.
O Buffet, D Aberdeen
ICAPS, 42-48, 2007
252007
Policy-gradients for PSRs and POMDPs
D Aberdeen, O Buffet, O Thomas
Artificial intelligence and statistics, 3-10, 2007
242007
Sorted inbox with important message identification based on global and user models
D Aberdeen, DS De Kloet, T Pietraszek, A Chen
US Patent 8,700,545, 2014
232014
Policy-gradient methods for planning
D Aberdeen
Advances in Neural Information Processing Systems 18, 2005
232005
Presentation of messages in multi-sectioned views
KJ Coleman, AW Moedinger, DJ Lauterbach, JB Cornwell, PM McDonald, ...
US Patent 8,793,591, 2014
202014
The factored policy gradient planner (ipc-06 version)
O Buffet, D Aberdeen
ICAPS 2006, 69, 2006
202006
92¢/mflops/s, ultra-large-scale neural-network training on a piii cluster
D Aberdeen, J Baxter, R Edwards
SC'00: Proceedings of the 2000 ACM/IEEE Conference on Supercomputing, 44-44, 2000
202000
The system can't perform the operation now. Try again later.
Articles 1–20