Douglas Aberdeen

Doug worked for several years in the field of Reinforcement Learning before joining Google. Within Google he works on Gmail including things like spam detection, but most recently including Priority Inbox.

Google Publications

Previous Publications

  •  

    The Factored Policy-Gradient Planner

    Olivier Buffet, Douglas Aberdeen

    Journal of Artificial Intelligence Research (JAIR), vol. 173 (2008), pp. 722-747

  •  

    Concurrent Probabilistic Temporal Planning with Policy-Gradients

    Douglas Aberdeen, Olivier Buffet

    Proceedings of the Seventeenth International Conference on Automated Planning and Scheduling (ICAPS'07), Providence, USA (2007)

  •  

    FF+FPG: Guiding a Policy-Gradient Planner

    Olivier Buffet, Douglas Aberdeen

    Proceedings of the Seventeenth International Conference on Automated Planning and Scheduling (ICAPS'07), Providence, USA (2007)

  •  

    Natural Actor-Critic for Road Traffic Optimisation

    Silvia Richter, Douglas Aberdeen, Jin Yu

    Advances in Neural Information Processing Systems, The {MIT} Press, Cambridge, MA (2007)

  •  

    Policy-Gradients for PSRs and POMDPs

    Douglas Aberdeen, Olivier Buffet, Owen Thomas

    Proc. 11th Intl. Conf. on Artificial Intelligence and Statistics (AIstats), Society for Artificial Intelligence and Statistics, San Juan, Puerto Rico (2007)

  •   

    Fast Online Policy Gradient Learning with SMD Gain Vector Adaptation

    Nicol N. Schraudolph, Jin Yu, Douglas Aberdeen

    Advances in Neural Information Processing Systems, The {MIT} Press, Cambridge, MA (2006), pp. 1185-1192

  •  

    Policy-Gradient Methods for Planning

    Douglas Aberdeen

    Advances in Neural Information Processing Systems, The {MIT} Press, Cambridge, MA (2006)

  •  

    Policy-Gradient for Robust Planning

    O. Buffet, D. Aberdeen

    Proceedings of the ECAI'06 Workshop on Planning, Learning and Monitoring with Uncertainty and Dynamic Worlds (PLMUDW'06) (2006)

  •  

    Policy-Gradient for Robust Planning (French)

    O. Buffet, D. Aberdeen

    Actes de la conférence francophone sur l'apprentissage automatique (CAp'06) (2006)

  •   

    The Factored Policy Gradient planner (IPC-06 Version)

    O. Buffet O., D. Aberdeen

    Proceedings of the Fifth International Planning Competition (2006)

  •  

    A Two-Teams Approach for Robust Probabilistic Temporal Planning

    O. Buffet, D. Aberdeen

    Proceedings of the ECML'05 workshop on Reinforcement Learning in Non-Stationary Environments (2005)

  •  

    Planification robuste avec (L)RTDP

    O. Buffet, D. Aberdeen

    Actes de la conférence francophone sur l'apprentissage automatique (CAp'05) (2005)

  •  

    Prottle: A Probabilistic Temporal Planner

    I. Little, D. Aberdeen, S. Thi\'ebaux

    Proc. AAAI'05 (2005)

  •  

    Robust Planning with (L)RTDP

    O. Buffet, D. Aberdeen

    Proceedings of the 19th International Joint Conference on Artificial Intelligence (IJCAI'05) (2005)

  •  

    Simulation Methods for Uncertain Decision-Theoretic Planning

    D. Aberdeen, O. Buffet

    Proceedings of the IJCAI 2005 Workshop on Planning and Learning in A Priori Unknown or Dynamic Domains

  •  

    Decision-Theoretic Military Operations Planning

    Douglas Aberdeen, Sylvie Thi\'ebaux, Lin Zhang

    Proc. ICAPS, AAAI (2004), pp. 402-411

  •  

    Filtered Reinforcement Learning

    Douglas Aberdeen

    Proceedings of the 15th European Conference on Machine Learning, Springer (2004), pp. 27-38

  •  

    Policy-Gradient Algorithms for Partially Observable Markov Decision Processes

    Douglas A. Aberdeen

    Ph.D. Thesis, The Australian National University (2003)

  •  

    Scaling Internal-State Policy-Gradient Methods for POMDPs

    Douglas Aberdeen, Jonathan Baxter

    Proceedings of the 19th International Conference on Machine Learning, Morgan Kaufmann, Syndey, Australia (2002)

  •  

    Emmerald: A fast Matrix-Matrix Multiply Using Intel SIMD Technology

    Douglas Aberdeen, Jonathan Baxter

    Concurrency and Computation: Practice and Experience, vol. 13 (2001), pp. 103-119

  •  

    92c /MFlop/s, Ultra-Large-Scale Neural-Network Training on a PIII Cluster

    Douglas Aberdeen, Jonathan Baxter, Robert Edwards

    Proceedings of Super Computing 2000, Dallas, TX.

  •  

    General Matrix-Matrix Multiplication Using SIMD features of the PIII

    Douglas Aberdeen, Jonathan Baxter

    Euro-Par 2000: Parallel Processing, Springer-Verlag, Munich, Germany