Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision Last revision Both sides next revision | ||
|
sdmia_schedule [2015/10/16 16:32] matthijs |
sdmia_schedule [2015/11/10 07:26] matthijs |
||
|---|---|---|---|
| Line 7: | Line 7: | ||
| ^ ^ ^ Authors ^ Title ^ | ^ ^ ^ Authors ^ Title ^ | ||
| |09:00am| 09:15am| Welcome and introductions || | |09:00am| 09:15am| Welcome and introductions || | ||
| - | |09:15am| 10:05am|Milind Tambe, USC |TBA| | + | |09:15am| 10:00am|Milind Tambe, USC |[[sdmia_invited_speakers|Assisting HIV Prevention Amongst Homeless Youth using POMDPs |
| - | |10:05am| 10:30am| application discussion || | + | ]]| |
| + | |10:00am| 10:30am| application discussion || | ||
| |10:30am| 11:00am| //Coffee break// || | |10:30am| 11:00am| //Coffee break// || | ||
| - | |11:00am| 11:45am|Shlomo Zilberstein, UMass Amherst |Do We Expect Too Much from DEC-POMDP Algorithms? | | + | |11:00am| 11:45am|Shlomo Zilberstein, UMass Amherst |[[sdmia_invited_speakers|Do We Expect Too Much from DEC-POMDP Algorithms?]] | |
| |11:45am| 12:10pm|C. Amato, G. Konidaris, S. Omidshafiei, A. Agha-Mohammadi, J. How and L. Kaelbling |Probabilistic Planning for Decentralized Multi-Robot Systems| | |11:45am| 12:10pm|C. Amato, G. Konidaris, S. Omidshafiei, A. Agha-Mohammadi, J. How and L. Kaelbling |Probabilistic Planning for Decentralized Multi-Robot Systems| | ||
| - | |12:10pm| 12:35pm|Siddharth Srivastava, Stuart Russell and Alessandro Pinto |Metaphysics of Planning Domain Descriptions | | + | |12:10pm| 12:35pm|S. Srivastava, S. Russell and A. Pinto |Metaphysics of Planning Domain Descriptions | |
| |12:35pm| 02:00pm| //Lunch// || | |12:35pm| 02:00pm| //Lunch// || | ||
| - | |02:00pm| 02:25pm |Erwin Walraven and Matthijs T. J. Spaan |Planning under Uncertainty with Weighted State Scenarios | | + | |02:00pm| 02:25pm |E. Walraven and M. T. J. Spaan |Planning under Uncertainty with Weighted State Scenarios | |
| - | |02:25pm| 02:50pm |Fabio-Valerio Ferrari and Abdel-Illah Mouaddib |Hierarchical factored POMDP for joint tasks : application to escort tasks | | + | |02:25pm| 02:50pm |F. Ferrari and A. Mouaddib |Hierarchical factored POMDP for joint tasks : application to escort tasks | |
| - | |02:50pm| 03:15pm |Luis Pineda, Kyle Wray and Shlomo Zilberstein |Revisiting Multi-Objective MDPs with Relaxed Lexicographic Preferences| | + | |02:50pm| 03:15pm |L. Pineda, K. Wray and S. Zilberstein |Revisiting Multi-Objective MDPs with Relaxed Lexicographic Preferences| |
| |03:15pm| 03:30pm | open discussion || | |03:15pm| 03:30pm | open discussion || | ||
| |03:30pm| 04:00pm | //Coffee break// || | |03:30pm| 04:00pm | //Coffee break// || | ||
| - | |04:00pm| 04:45pm |Mykel Kochenderfer, Stanford |Decision Theoretic Planning for Air Traffic Applications| | + | |04:00pm| 04:45pm |Mykel Kochenderfer, Stanford |[[sdmia_invited_speakers|Decision Theoretic Planning for Air Traffic Applications]]| |
| - | |04:45pm| 05:10pm |A. Reyes, P. H. Ibarguengoytia, I. Romero, D. Pech and M. Borunda |Open questions for building optimal operation policies for dam management using Factored Markov Decision Processes | | + | |04:45pm| 05:10pm |B. Lacerda, D. Parker and N. Hawes |Nested Value Iteration for Partially Satisfiable Co-Safe LTL Specifications (Extended Abstract) | |
| - | |05:10pm| 05:35pm |Kyle Wray and Shlomo Zilberstein |A Parallel Point-Based POMDP Algorithm Leveraging GPUs | | + | |05:10pm| 05:35pm |K. Wray and S. Zilberstein |A Parallel Point-Based POMDP Algorithm Leveraging GPUs | |
| |06:00pm| 07:00pm | //Reception// || | |06:00pm| 07:00pm | //Reception// || | ||
| Line 27: | Line 28: | ||
| ^ ^ ^ Authors ^ Title ^ | ^ ^ ^ Authors ^ Title ^ | ||
| - | |09:00am| 09:45am |Jason Williams, Microsoft Research |Decision-theoretic control in dialog systems: recent progress and opportunities for research| | + | |09:00am| 09:45am |Jason Williams, Microsoft Research |[[sdmia_invited_speakers|Decision-theoretic control in dialog systems: recent progress and opportunities for research]]| |
| |09:45am| 10:05am | application discussion || | |09:45am| 10:05am | application discussion || | ||
| - | |10:05am| 10:30am |Daniel Urieli and Peter Stone |Autonomous Electricity Trading using Time-Of-Use Tariffs in a Competitive Market | | + | |10:05am| 10:30am |D. Urieli and P. Stone |Autonomous Electricity Trading using Time-Of-Use Tariffs in a Competitive Market | |
| |10:30am| 11:00am | //Coffee break// || | |10:30am| 11:00am | //Coffee break// || | ||
| - | |11:00am| 11:25am |Edmund Durfee and Satinder Singh |Commitment Semantics for Sequential Decision Making Under Reward Uncertainty | | + | |11:00am| 11:25am |E. Durfee and S. Singh |Commitment Semantics for Sequential Decision Making Under Reward Uncertainty | |
| |11:25am| 11:50am |A. Iwasaki, T. Sekiguchi, S. Yamamoto and M. Yokoo |How is cooperation/collusion sustained in repeated multimarket contact with observation errors? | | |11:25am| 11:50am |A. Iwasaki, T. Sekiguchi, S. Yamamoto and M. Yokoo |How is cooperation/collusion sustained in repeated multimarket contact with observation errors? | | ||
| - | |11:50am| 12:10pm |S. Mcgregor, H. Buckingham, R. Houtman, C. Montgomery, R. Metoyer and T. Dietterich |Facilitating Testing and Debugging of Markov Decision Processes with Interactive Visualization | | + | |11:50am| 12:10pm |S. Mcgregor, H. Buckingham, R. Houtman, C. Montgomery, R. Metoyer and T. Dietterich |MDPvis: An Interactive Visualization for Testing Markov Decision Processes | |
| - | |12:10pm| 12:30pm |Frans Oliehoek, Matthijs T. J. Spaan, Philipp Robbel and Joao Messias |The MADP Toolbox: An Open-Source Library for Planning and Learning in (Multi-)Agent Systems | | + | |12:10pm| 12:30pm |F. Oliehoek, M. T. J. Spaan, P. Robbel and J. Messias |The MADP Toolbox: An Open-Source Library for Planning and Learning in (Multi-)Agent Systems | |
| |12:30pm| 02:00pm | //Lunch// || | |12:30pm| 02:00pm | //Lunch// || | ||
| - | |02:00pm| 02:45pm |Craig Boutilier, Google |Large-scale MDPs in Practice: Opportunities and Challenges | | + | |02:00pm| 02:45pm |Craig Boutilier, Google |[[sdmia_invited_speakers|Large-scale MDPs in Practice: Opportunities and Challenges]] | |
| |02:45pm| 03:00pm | application discussion || | |02:45pm| 03:00pm | application discussion || | ||
| - | |03:00pm| 03:25pm |Philipp Robbel, Frans A. Oliehoek and Mykel J. Kochenderfer |Exploiting Anonymity in Approximate Linear Programming: Scaling to Large Multiagent MDPs | | + | |03:00pm| 03:25pm |P. Robbel, F. A. Oliehoek and M. J. Kochenderfer |Exploiting Anonymity in Approximate Linear Programming: Scaling to Large Multiagent MDPs | |
| |03:30pm| 04:00pm | //Coffee break// || | |03:30pm| 04:00pm | //Coffee break// || | ||
| - | |04:00pm| 04:45pm |Emma Brunskill, CMU |Quickly Learning to Make Good Decisions | | + | |04:00pm| 04:45pm |Emma Brunskill, CMU |[[sdmia_invited_speakers|Quickly Learning to Make Good Decisions]] | |
| - | |04:45pm| 05:10pm |Martin Allen |Complexity of Self-Preserving, Team-Based Competition in Partially Observable Stochastic Games | | + | |04:45pm| 05:10pm |M. Allen |Complexity of Self-Preserving, Team-Based Competition in Partially Observable Stochastic Games | |
| - | |05:10pm| 05:35pm |Bruno Lacerda, David Parker and Nick Hawes |Nested Value Iteration for Partially Satisfiable Co-Safe LTL Specifications (Extended Abstract) | | + | |05:10pm| 05:35pm |M. Hausknecht and P. Stone |Deep Recurrent Q-Learning for Partially Observable MDPs | |
| |06:00pm| 07:30pm | //Plenary session// || | |06:00pm| 07:30pm | //Plenary session// || | ||
| Line 48: | Line 49: | ||
| ^ ^ ^ Authors ^ Title ^ | ^ ^ ^ Authors ^ Title ^ | ||
| - | |09:00am| 09:45am |Alan Fern, Oregon State |Quickly Learning to Make Good Decisions | | + | |09:00am| 09:45am |Alan Fern, Oregon State |[[sdmia_invited_speakers|Learning to Speedup Planning: Filling the Gap Between Reaction and |
| + | Thinking]] | | ||
| |09:45am| 10:00am | application discussion || | |09:45am| 10:00am | application discussion || | ||
| - | |10:00am| 10:25am |Matthew Hausknecht and Peter Stone |Deep Recurrent Q-Learning for Partially Observable MDPs | | + | |10:00am| 10:25am |A. Reyes, P. H. Ibarguengoytia, I. Romero, D. Pech and M. Borunda |Open questions for building optimal operation policies for dam management using Factored Markov Decision Processes | |
| |10:30am| 11:00am | //Coffee break// || | |10:30am| 11:00am | //Coffee break// || | ||
| - | |11:00am| 11:25am |D. Ellis Hershkowitz, James MacGlashan and Stefanie Tellex |Learning Propositional Functions for Planning and Reinforcement Learning | | + | |11:00am| 11:25am |D. E. Hershkowitz, J. MacGlashan and S. Tellex |Learning Propositional Functions for Planning and Reinforcement Learning | |
| - | |11:25am| 11:50am |Yusen Zhan and Matthew Taylor |Online Transfer Learning in Reinforcement Learning Domains | | + | |11:25am| 11:50am |Y. Zhan and M. Taylor |Online Transfer Learning in Reinforcement Learning Domains | |
| |11:50am| 12:30pm | wrapup discussion || | |11:50am| 12:30pm | wrapup discussion || | ||
