2008 |
53 | EE | Michael H. Bowling,
Alborz Geramifard,
David Wingate:
Sigma point policy iteration.
AAMAS (1) 2008: 379-386 |
52 | EE | James Neufeld,
Michael Sokolsky,
Jason Roberts,
Adam Milstein,
Stephen Walsh,
Michael H. Bowling:
Autonomous geocaching: navigation and goal finding in outdoor domains.
AAMAS (1) 2008: 47-54 |
51 | | Maria Cutumisu,
Duane Szafron,
Michael H. Bowling,
Richard S. Sutton:
Agent Learning using Action-Dependent Learning Rates in Computer Role-Playing Games.
AIIDE 2008 |
50 | EE | Umar Syed,
Michael H. Bowling,
Robert E. Schapire:
Apprenticeship learning using linear programming.
ICML 2008: 1032-1039 |
49 | EE | Michael H. Bowling,
Michael Johanson,
Neil Burch,
Duane Szafron:
Strategy evaluation in extensive games with importance sampling.
ICML 2008: 72-79 |
48 | EE | Nathan R. Sturtevant,
H. James Hoover,
Jonathan Schaeffer,
Sean Gouglas,
Michael H. Bowling,
Finnegan Southey,
Matthew Bouchard,
Ghassan Zabaneh:
Multidisciplinary students and instructors: a second-year games course.
SIGCSE 2008: 383-387 |
47 | EE | Richard S. Sutton,
Csaba Szepesvári,
Alborz Geramifard,
Michael H. Bowling:
Dyna-Style Planning with Linear Function Approximation and Prioritized Sweeping.
UAI 2008: 528-536 |
2007 |
46 | | Nolan Bard,
Michael H. Bowling:
Particle Filtering for Dynamic Agent Modelling in Simplified Poker.
AAAI 2007: 515-514 |
45 | | Martin Zinkevich,
Michael H. Bowling,
Neil Burch:
A New Algorithm for Generating Equilibria in Massive Zero-Sum Games.
AAAI 2007: 788- |
44 | EE | Daniel J. Lizotte,
Tao Wang,
Michael H. Bowling,
Dale Schuurmans:
Automatic Gait Optimization with Gaussian Process Regression.
IJCAI 2007: 944-949 |
43 | EE | Michael Johanson,
Martin Zinkevich,
Michael H. Bowling:
Computing Robust Counter-Strategies.
NIPS 2007 |
42 | EE | Martin Zinkevich,
Michael Johanson,
Michael H. Bowling,
Carmelo Piccione:
Regret Minimization in Games with Incomplete Information.
NIPS 2007 |
41 | EE | Tao Wang,
Daniel J. Lizotte,
Michael H. Bowling,
Dale Schuurmans:
Stable Dual Dynamic Programming.
NIPS 2007 |
2006 |
40 | | Armita Kaboli,
Michael H. Bowling,
Petr Musílek:
Bayesian Calibration for Monte Carlo Localization.
AAAI 2006 |
39 | | Achim Rettinger,
Martin Zinkevich,
Michael H. Bowling:
Boosting Expert Ensembles for Rapid Concept Recall.
AAAI 2006 |
38 | | Tao Wang,
Pascal Poupart,
Michael H. Bowling,
Dale Schuurmans:
Compact, Convex Upper Bound Iteration for Approximate POMDP Planning.
AAAI 2006 |
37 | | Alborz Geramifard,
Michael H. Bowling,
Richard S. Sutton:
Incremental Least-Squares Temporal Difference Learning.
AAAI 2006 |
36 | | Martin Zinkevich,
Michael H. Bowling,
Nolan Bard,
Morgan Kan,
Darse Billings:
Optimal Unbiased Estimators for Evaluating Agent Performance.
AAAI 2006 |
35 | | Nathan R. Sturtevant,
Martin Zinkevich,
Michael H. Bowling:
Prob-Maxn: Playing N-Player Games with Opponent Models.
AAAI 2006 |
34 | | Michael H. Bowling,
Dana F. Wilkinson,
Ali Ghodsi:
Subjective Mapping.
AAAI 2006 |
33 | EE | Nathan R. Sturtevant,
Michael H. Bowling:
Robust game play against unknown opponents.
AAMAS 2006: 713-719 |
32 | EE | Michael H. Bowling,
Peter McCracken,
Michael James,
James Neufeld,
Dana F. Wilkinson:
Learning predictive state representations using non-blind policies.
ICML 2006: 129-136 |
31 | EE | Alborz Geramifard,
Michael H. Bowling,
Martin Zinkevich,
Richard S. Sutton:
iLSTD: Eligibility Traces and Convergence Analysis.
NIPS 2006: 441-448 |
30 | EE | Michael H. Bowling,
Johannes Fürnkranz,
Thore Graepel,
Ron Musick:
Machine learning and games.
Machine Learning 63(3): 211-215 (2006) |
2005 |
29 | | Michael H. Bowling,
Peter McCracken:
Coordination and Adaptation in Impromptu Teams.
AAAI 2005: 53-58 |
28 | EE | Michael H. Bowling,
Ali Ghodsi,
Dana F. Wilkinson:
Action respecting embedding.
ICML 2005: 65-72 |
27 | EE | Tao Wang,
Daniel J. Lizotte,
Michael H. Bowling,
Dale Schuurmans:
Bayesian sparse sampling for on-line reward optimization.
ICML 2005: 956-963 |
26 | EE | Dana F. Wilkinson,
Michael H. Bowling,
Ali Ghodsi:
Learning Subjective Representations for Planning.
IJCAI 2005: 889-894 |
25 | EE | Michael H. Bowling,
Dana F. Wilkinson,
Ali Ghodsi,
Adam Milstein:
Subjective Localization with Action Respecting Embedding.
ISRR 2005: 190-202 |
24 | EE | Peter McCracken,
Michael H. Bowling:
Online Discovery and Learning of Predictive State Representations.
NIPS 2005 |
23 | EE | Finnegan Southey,
Michael H. Bowling,
Bryce Larson,
Carmelo Piccione,
Neil Burch,
Darse Billings,
D. Chris Rayner:
Bayes? Bluff: Opponent Modelling in Poker.
UAI 2005: 550-558 |
2004 |
22 | EE | Darse Billings,
Aaron Davidson,
Terence Schauenberg,
Neil Burch,
Michael H. Bowling,
Robert C. Holte,
Jonathan Schaeffer,
Duane Szafron:
Game-Tree Search with Adaptation in Stochastic Imperfect-Information Games.
Computers and Games 2004: 21-34 |
21 | | Michael H. Bowling,
Brett Browning,
Manuela M. Veloso:
Plays as Effective Multiagent Plans Enabling Opponent-Adaptive Play Selection.
ICAPS 2004: 376-383 |
20 | EE | Michael H. Bowling:
Convergence and No-Regret in Multiagent Learning.
NIPS 2004 |
19 | EE | Michael H. Bowling,
Manuela M. Veloso:
Existence of Multiagent Equilibria with Limited Agents.
J. Artif. Intell. Res. (JAIR) 22: 353-384 (2004) |
2003 |
18 | | James Bruce,
Michael H. Bowling,
Brett Browning,
Manuela M. Veloso:
Multi-robot team response to a multi-robot opponent team.
ICRA 2003: 2281-2286 |
17 | | Michael H. Bowling,
Rune M. Jensen,
Manuela M. Veloso:
A Formalization of Equilibria for Multiagent Planning.
IJCAI 2003: 1460-1462 |
16 | | Michael H. Bowling,
Manuela M. Veloso:
Simultaneous Adversarial Multi-Robot Learning.
IJCAI 2003: 699-704 |
15 | EE | Michael H. Bowling,
Brett Browning,
Allen Chang,
Manuela M. Veloso:
Plays as Team Plans for Coordination and Adaptation.
RoboCup 2003: 686-693 |
2002 |
14 | EE | Gal A. Kaminka,
Michael H. Bowling:
Towards robust teams with many agents.
AAMAS 2002: 729-736 |
13 | | Brett Browning,
Michael H. Bowling,
Manuela M. Veloso:
Improbability Filtering for Rejecting False Positives.
ICRA 2002: 3038-3043 |
12 | EE | Michael H. Bowling:
Approximation Techniques in Multiagent Learning.
SARA 2002: 328-329 |
11 | EE | Michael H. Bowling,
Manuela M. Veloso:
Multiagent learning using a variable learning rate.
Artif. Intell. 136(2): 215-250 (2002) |
2001 |
10 | | Michael H. Bowling,
Manuela M. Veloso:
Convergence of Gradient Dynamics with a Variable Learning Rate.
ICML 2001: 27-34 |
9 | | Michael H. Bowling,
Manuela M. Veloso:
Rational and Convergent Learning in Stochastic Games.
IJCAI 2001: 1021-1026 |
8 | EE | Brett Browning,
Michael H. Bowling,
James Bruce,
Ravi Balasubramanian,
Manuela M. Veloso:
CM-Dragons'01 - Vision-Based Motion Tracking and Heteregenous Robots.
RoboCup 2001: 567-570 |
2000 |
7 | | Michael H. Bowling:
Convergence Problems of General-Sum Multiagent Reinforcement Learning.
ICML 2000: 89-94 |
6 | | Manuela M. Veloso,
Michael H. Bowling,
Sorin Achim,
Kwun Han,
Peter Stone:
CMUNITED-98: RoboCup-98 Small-Robot World Champion Team.
AI Magazine 21(1): 29-36 (2000) |
1999 |
5 | | Manuela M. Veloso,
Michael H. Bowling,
Sorin Achim,
Kwun Han,
Peter Stone:
CMUnited-98: A Team of Robotic Soccer Agents.
AAAI/IAAI 1999: 891-896 |
4 | | Michael H. Bowling,
Manuela M. Veloso:
Bounding the Suboptimality of Reusing Subproblem.
IJCAI 1999: 1340-1347 |
3 | | Michael H. Bowling,
Manuela M. Veloso:
Motion Control in Dynamic Multi-Robot Environments.
RoboCup 1999: 222-230 |
2 | | Manuela M. Veloso,
Michael H. Bowling,
Sorin Achim:
CMUnited-99: Small-Size Robot Team.
RoboCup 1999: 661-662 |
1998 |
1 | EE | Manuela M. Veloso,
Michael H. Bowling,
Sorin Achim,
Kwun Han,
Peter Stone:
The CMUnited-98 Small-Robot Team.
RoboCup 1998: 77-92 |