Award Winner
- Dual Representations for Dynamic Programming and Reinforcement Learning. Tao Wang, Michael Bowling, and Dale Schuurmans. In Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, pp. 44–51, April 2007.
- STP: Skills, tactics and plays for multi-robot control in adversarial environments. Brett Browning, James Bruce, Michael Bowling, and Manuela Veloso. Journal of Systems and Control Engineering, 219(1):33–52, 2005.
- Multiagent Learning in the Presence of Agents with Limitations. Michael Bowling. Ph.D. Thesis, Computer Science Department, Carnegie Mellon University, Pittsburgh, PA, 2003. Available as technical report CMU-CS-03-118
topJournal
- The Arcade Learning Environment: An Evaluation Platform for General Agents. Marc G. Bellemare, Yavar Naddaf, Joel Veness, and Michael Bowling. Journal of Artificial Intelligence Research, 2013. To Appear
- Linear Fitted-Q Iteration with Multiple Reward Functions. Daniel J. Lizotte, Michael Bowling, and Susan A. Murphy. Journal of Machine Learning Research, 13:3253–3295, 2012.
- STP: Skills, tactics and plays for multi-robot control in adversarial environments. Brett Browning, James Bruce, Michael Bowling, and Manuela Veloso. Journal of Systems and Control Engineering, 219(1):33–52, 2005.
- Existence of Multiagent Equilibria with Limited Agents. Michael Bowling and Manuela Veloso. Journal of Artificial Intelligence Research, 22:353–384, 2004. A previous version appeared as a CMU Technical Report, CMU-CS-02-104.
- Multiagent Learning Using a Variable Learning Rate. Michael Bowling and Manuela Veloso. Artificial Intelligence, 136:215–250, 2002.
- The CMUnited-98 Champion Small Robot Team. Manuela Veloso, Michael Bowling, Sorin Achim, Kwun Han, and Peter Stone. Advanced Robotics, 2000. An earlier version appeared in RoboCup-98: Robot Soccer World Cup II, Asada and Kitano (Eds.), Springer, 1999, pages 77–92. A shorter version appeared in the AI Magazine, 21:29–36
topRefereed Conference
- A Randomized Mirror Descent Algorithm for Large Scale Multiple Kernel Learning. Arash Afkanpour, András György, Csaba Szepesvári, and Michael Bowling. In Proceedings of the Thirtieth International Conference on Machine Learning (ICML), 2013. To Appear
- Online Implicit Agent Modelling. Nolan Bard, Michael Johanson, Neil Burch, and Michael Bowling. In Proceedings of the Twelfth International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2013. To Appear
- Sketch-Based Linear Value Function Approximation. Marc G. Bellemare, Joel Veness, and Michael Bowling. In NIPS13, 2013. To Appear
- Tractable Objectives for Robust Policy Optimization. Katherine Chen and Michael Bowling. In Advances in Neural Information Processing Systems 25 (NIPS), 2013. To Appear
- Baseline: Practical Control Variates for Agent Evaluation in Zero-Sum Domains. Joshua Davidson, Christopher Archibald, and Michael Bowling. In Proceedings of the Twelfth International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2013. To Appear
- Evaluating State-Space Abstractions in Extensive-Form Games. Michael Johanson, Neil Burch, Richard Valenzano, and Michael Bowling. In Proceedings of the Twelfth International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2013. To Appear
- Partition Tree Weighting. Joel Veness, Martha White, Michael Bowling, and András György. In Proceedings of the Data Compression Conference (DCC), 2013. To Appear
- On Local Regret. Michael Bowling and Martin Zinkevich. In Proceedings of the Twenty-Ninth International Conference on Machine Learning (ICML), pp. 1631–1638, 2012. A longer version is available as a University of Alberta Technical Report, TR12-04.
- Investigating Contingency Awareness using Atari 2600 Games. Marc Gendron-Bellemare, Joel Veness, and Michael Bowling. In Proceedings of the Twenty-Sixth Conference on Artificial Intelligence (AAAI), pp. 864–871, 2012.
- Generalized Sampling and Variance in Counterfactual Regret Minimization. Richard Gibson, Marc Lanctot, Neil Burch, Duane Szafron, and Michael Bowling. In Proceedings of the Twenty-Sixth Conference on Artificial Intelligence (AAAI), pp. 1355–1361, 2012. A longer version is available as a University of Alberta Technical Report, TR12-02.
- Finding Optimal Abstract Strategies in Extensive Form Games. Michael Johanson, Nolan Bard, Neil Burch, and Michael Bowling. In Proceedings of the Twenty-Sixth Conference on Artificial Intelligence (AAAI), pp. 1371–1379, 2012.
- Efficient Nash Equilibrium Approximation through Monte Carlo Counterfactual Regret Minimization. Michael Johanson, Nolan Bard, Marc Lanctot, Richard Gibson, and Michael Bowling. In Proceedings of the Eleventh International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), pp. 837–844, 2012.
- No-Regret Learning in Extensive-Form Games with Imperfect Recall. Marc Lanctot, Richard Gibson, Neil Burch, and Michael Bowling. In Proceedings of the Twenty-Ninth International Conference on Machine Learning (ICML), pp. 65–72, 2012. A longer version is available as a University of Alberta Technical Report, TR12-04.
- Context Tree Switching. Joel Veness, Kee Siong Ng, Marcus Hutter, and Michael Bowling. In Proceedings of the Data Compression Conference (DCC), pp. 327–336, 2012.
- Variance Reduction in Monte Carlo Tree Search. Joel Veness, Marc Lanctot, and Michael Bowling. In Advances in Neural Information Processing Systems 24 (NIPS), pp. 1836–1844, 2012.
- Accelerating Best Response Calculation in Large Extensive Games. Michael Johanson, Michael Bowling, Kevin Waugh, and Martin Zinkevich. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI), pp. 258–265, 2011.
- Euclidean Heuristic Optimization. Chris Rayner, Michael Bowling, and Nathan Sturtevant. In Proceedings of the Twenty-Fifth Conference on Artificial Intelligence (AAAI), pp. 81–86, 2011.
- Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis. Daniel J. Lizotte, Michael Bowling, and Susan A. Murphy. In Proceedings of the Twenty-Seventh International Conference on Machine Learning (ICML), pp. 695–702, 2010.
- Data Biased Robust Counter Strategies. Michael Johanson and Michael Bowling. In Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 264–271, 2009.
- Monte Carlo Sampling for Regret Minimization in Extensive Games. Marc Lanctot, Kevin Waugh, Martin Zinkevich, and Michael Bowling. In Advances in Neural Information Processing Systems 22 (NIPS), pp. 1078–1086, 2009. A longer version is available as a University of Alberta Technical Report, TR09-15. An earlier version appeared in the COLT Workshop on On-Line Learning with Limited Feedback (2009).
- Probabilistic state translation in extensive games with large action sets. David Schnizlein, Michael Bowling, and Duane Szafron. In Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence (IJCAI), pp. 276–284, 2009.
- Abstraction Pathologies in Extensive Games. Kevin Waugh, Dave Schnizlein, Michael Bowling, and Duane Szafron. In Proceedings of the Eighth International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), pp. 781–788, 2009.
- Learning a Value Analysis Tool For Agent Evaluation. Martha White and Michael Bowling. In Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence (IJCAI), pp. 1976–1981, 2009.
- Strategy Evaluation in Extensive Games with Importance Sampling. Michael Bowling, Michael Johanson, Neil Burch, and Duane Szafron. In Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML), pp. 72–79, 2008.
- Sigma Point Policy Iteration. Michael Bowling, Alborz Geramifard, and David Wingate. In Proceedings of the Seventh International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), pp. 379–386, 2008.
- Agent Learning using Action-Dependent Learning Rates in Computer Role-Playing Games. Maria Cutumisu, Duane Szafron, Michael Bowling, and Richard S. Sutton. In Proceedings of the Fourth Conference onArtificial Intelligence and Interactive Digital Entertainment (AIIDE), 2008.
- Computing Robust Counter-Strategies. Michael Johanson, Martin Zinkevich, and Michael Bowling. In Advances in Neural Information Processing Systems 20 (NIPS), pp. 1128–1135, 2008. A longer version is available as a University of Alberta Technical Report, TR07-15.
- Autonomous Geocaching: Navigation and Goal Finding in Outdoor Domains. James Neufeld, Jason Roberts, Stephen Walsh, Michael Sokolsky, Adam Milstein, and Michael Bowling. In Proceedings of the Seventh International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), pp. 47–54, 2008.
- Multidisciplinary Students And Instructors: A Second-Year Games Course. Nathan Sturtevant, H. James Hoover, Jonathan Schaeffer, Sean Gouglas, Michael Bowling, Finnegan Southey, Matthew Bouchard, and Ghassan Zabaneh. In Proceedings of the Thirty-Ninth ACM Technical Symposium on Computer Science Education (SIGCSE), pp. 383–387, 2008.
- Dyna-style Planning with Linear Function Approximation and Prioritized Sweeping. Richard Sutton, Csaba Szepesvari, Alborz Geramifard, and Michael Bowling. In Proceedings of the Twenty-Fourth Conference on Uncertaintyin Artificial Intelligence (UAI), pp. 528–536, 2008.
- Apprenticeship Learning Using Linear Programming. Umar Syed, Robert Schapire, and Michael Bowling. In Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML), pp. 1032–1039, 2008.
- Stable Dual Dynamic Programming. Tao Wang, Daniel Lizotte, Michael Bowling, and Dale Schuurmans. In Advances in Neural Information Processing Systems 20 (NIPS), pp. 713–720, 2008.
- Regret Minimization in Games with Incomplete Information. Martin Zinkevich, Michael Johanson, Michael Bowling, and Carmelo Piccione. In Advances in Neural Information Processing Systems 20 (NIPS), pp. 905–912, 2008. A longer version is available as a University of Alberta Technical Report, TR07-14.
- Particle Filtering for Dynamic Agent Modelling in Simplified Poker. Nolan Bard and Michael Bowling. In Proceedings of the Twenty-Second Conference on Artificial Intelligence (AAAI), pp. 515–521, 2007.
- iLSTD: Eligibility Traces and Convergence Analysis. Alborz Geramifard, Michael Bowling, Martin Zinkevich, and Richard S. Sutton. In Advances in Neural Information Processing Systems 19 (NIPS), pp. 441–448, 2007.
- Automatic Gait Optimization with Gaussian Process Regression. Daniel Lizotte, Tao Wang, Michael Bowling, and Dale Schuurmans. In Proceedings of the Twentieth International Joint Conference on Artificial Intelligence (IJCAI), pp. 944–949, 2007.
- A New Algorithm for Generating Equilibria in Massive Zero-Sum Games. Martin Zinkevich, Michael Bowling, and Neil Burch. In Proceedings of the Twenty-Second Conference on Artificial Intelligence (AAAI), pp. 788–793, 2007.
- Subjective Mapping. Michael Bowling, Dana Wilkinson, and Ali Ghodsi. In New Scientific and Technical Advances in Research (NECTAR) of the Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI), pp. 1569–1572, 2006.
- Learning Predictive State Representations Using Non-Blind Policies. Michael Bowling, Peter McCracken, Michael James, James Neufeld, and Dana Wilkinson. In Proceedings of the Twenty-Third International Conference on Machine Learning (ICML), pp. 129–136, 2006.
- Incremental Least-Squares Temporal Difference Learning. Alborz Geramifard, Michael Bowling, and Richard S. Sutton. In Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI), pp. 356–361, 2006.
- Bayesian Calibration for Monte Carlo Localization. Armita Kaboli, Michael Bowling, and Petr Musilek. In Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI), pp. 964–969, 2006.
- Online Discovery and Learning of Predictive State Representations. Peter McCracken and Michael Bowling. In Advances in Neural Information Processing Systems 18 (NIPS), pp. 875–882, 2006.
- Boosting Expert Ensembles for Rapid Concept Recall. Achim Rettinger, Martin Zinkevich, and Michael Bowling. In Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI), pp. 464–469, 2006.
- ProbMaxn: Opponent Modeling in N-Player Games. Nathan Sturtevant, Martin Zinkevich, and Michael Bowling. In Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI), pp. 1057–1063, 2006.
- Robust Game Play Against Unknown Opponents. Nathan Sturtevant and Michael Bowling. In Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), pp. 713–719, 2006.
- Compact, Convex Upper Bound Iteration for Approximate POMDP Planning. Tao Wang, Pascal Poupart, Michael Bowling, and Dale Schuurmans. In Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI), pp. 1245–1251, 2006.
- Optimal Unbiased Estimators for Evaluating Agent Performance. Martin Zinkevich, Michael Bowling, Nolan Bard, Morgan Kan, and Darse Billings. In Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI), pp. 573–578, 2006.
- Subjective Localization with Action Respecting Embedding. Michael Bowling, Dana Wilkinson, Ali Ghodsi, and Adam Milstein. In Proceedings of the International Symposium of Robotics Research (ISRR), 2005.
- Action Respecting Embedding. Michael Bowling, Ali Ghodsi, and Dana Wilkinson. In Proceedings of the Twenty-Second International Conference on Machine Learning (ICML), pp. 65–72, 2005.
- Coordination and Adaptation in Impromptu Teams. Michael Bowling and Peter McCracken. In Proceedings of the Twentieth National Conference on Artificial Intelligence (AAAI), pp. 53–58, 2005.
- Convergence and No-Regret in Multiagent Learning. Michael Bowling. In Advances in Neural Information Processing Systems 17 (NIPS), pp. 209–216, 2005. A longer version is available as a University of Alberta Technical Report, TR04-11.
- Bayes' Bluff: Opponent Modelling in Poker. Finnegan Southey, Michael Bowling, Bryce Larson, Carmelo Piccione, Neil Burch, Darse Billings, and Chris Rayner. In Proceedings of the Twenty-First Conference on Uncertaintyin Artificial Intelligence (UAI), pp. 550–558, 2005.
- Bayesian Sparse Sampling for On-line Reward Optimization. Tao Wang, Daniel Lizotte, Michael Bowling, and Dale Schuurmans. In Proceedings of the Twenty-Second International Conference on Machine Learning (ICML), pp. 961–968, 2005.
- Learning Subjective Representations for Planning. Dana Wilkinson, Michael Bowling, and Ali Ghodsi. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence (IJCAI), pp. 889–894, 2005.
- Game tree search with adaptation in stochastic imperfect information games. Darse Billings, Aaron Davidson, Terence Schauenberg, Neil Burch, Michael Bowling, Robert Holte, Jonathan Schaeffer, and Duane Szafron. In Computers and Games (CG), 2004.
- Plays as Effective Multiagent Plans Enabling Opponent-Adaptive Play Selection. Michael Bowling, Brett Browning, and Manuela Veloso. In Proceedings of the Fourteenth International Conference on Automated Planning and Scheduling (ICAPS), pp. 376–383, 2004.
- Simultaneous Adversarial Multi-Robot Learning. Michael Bowling and Manuela Veloso. In Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI), pp. 699–704, August 2003.
- Multi-Robot Team Response to a Multi-Robot Opponent Team. James Bruce, Michael Bowling, Brett Browning, and Manuela Veloso. In Proceedings of the 2003 IEEE International Conference on Robotics and Automation (ICRA), pp. 2281–2286, 2003. An earlier version appeared in the IROS Workshop on Collaborative Robotics (2002)
- Improbability Filtering for Rejecting False Positives. Brett Browning, Michael Bowling, and Manuela Veloso. In Proceedings of the 2002 IEEE International Conference on Robotics and Automation (ICRA), pp. 3038–3043, May 2002.
- Towards Robust Teams with Many Agents. Gal A. Kaminka and Michael Bowling. In Proceedings of the First International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), pp. 729–736, July 2002.
- Rational and Convergent Learning in Stochastic Games. Michael Bowling and Manuela Veloso. In Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI), pp. 1021–1026, August 2001.
- Convergence of Gradient Dynamics with a Variable Learning Rate. Michael Bowling and Manuela Veloso. In Proceedings of the Eighteenth International Conference on Machine Learning (ICML), pp. 27–34, June 2001.
- Convergence Problems of General-Sum Multiagent Reinforcement Learning. Michael Bowling. In Proceedings of the Seventeenth International Conference on Machine Learning (ICML), pp. 89–94, June 2000.
- Bounding the Suboptimality of Reusing Subproblems. Michael Bowling and Manuela Veloso. In Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence (IJCAI), pp. 1340–1345, August 1999. An earlier version appeared in the Proceedings of the NIPS Workshop on Abstraction in Reinforcement Learning (1998)
- CMUnited-98: A Team of Robotic Soccer Agents. Manuela Veloso, Michael Bowling, Sorin Achim, Kwun Han, and Peter Stone. In Proceedings of the Eleventh Innovative Applications of Artificial Intelligence (IAAI), pp. 891–896, 1999.
topSymposia/Workshop
- A Practical Use of Imperfect Recall. Kevin Waugh, Martin Zinkevich, Michael Johanson, Morgan Kan, David Schnizlein, and Michael Bowling. In Proceedings of the Eighth Symposium on Abstraction, Reformulation and Approximation (SARA), pp. 175–182, 2009.
- Scalable Action Respecting Embedding. Michael Biggs, Ali Ghodsi, Dana Wilkinson, and Michael Bowling. In Proceedings of the Tenth International Symposium on Artificial Intelligence and Mathematics (ISAIM), 2008.
- Dual Representations for Dynamic Programming and Reinforcement Learning. Tao Wang, Michael Bowling, and Dale Schuurmans. In Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, pp. 44–51, April 2007.
- Safe Strategies for Agent Modelling in Games. Peter McCracken and Michael Bowling. In AAAI Fall Symposium on Artificial Multi-agent Learning, October 2004.
- Plays as Team Plans for Cooperation and Adaptation. Michael Bowling, Brett Browning, Allen Chang, and Manuela Veloso. In IJCAI Workshop on Issues in Designing Physical Agents for Dynamic Real-Time Environments: World Modelling, Planning, Learning, and Communicating, August 2003.
- Scalable Learning in Stochastic Games. Michael Bowling and Manuela Veloso. In AAAI Workshop on Game Theoretic and Decision Theoretic Agents, July 2002.
- A Formalization of Equilibria for Multiagent Planning. Michael Bowling, Rune Jensen, and Manuela Veloso. In AAAI Workshop on Planning with and for Multiagent Systems, July 2002.
- OBDD-Based Optimistic and Strong Cyclic Adversarial Planning. Rune Jensen, Manuela Veloso, and Michael Bowling. In Proceedings of the Sixth European Conference on Planning (ECP), pp. 265–276, September 2001.
- Motion Control in Dynamic Multi-Robot Environments. Michael Bowling and Manuela Veloso. In Proceedings of the 1999 IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA), pp. 168–173, November 1999.
- Anticipation as A Key for Collaboration in a Team of Agents: A Case Study in Robotic Soccer. Manuela Veloso, Peter Stone, and Michael Bowling. In Proceedings of SPIE Sensor Fusion and Decentralized Control in Robotic Systems II, 3839, September 1999.
- Reusing Learned Policies Between Similar Problems. Michael Bowling and Manuela Veloso. In Proceedings of the AI*IA-98 Workshop on New Trends in Robotics, October 1998.
- Predictive Memory for an Inaccessible Environment. Michael Bowling, Peter Stone, and Manuela Veloso. In Working Notes of the IROS-96 Workshop on RoboCup, November 1996.
topUnrefereed Collection
- Research in Image Understanding and Automated Cartography: 1995-1996. David M. McKeown, Jr., Michael Bowling, G. Edward Bulwinkle, Steven Douglas Cochran, Stephen J. Ford, Wilson A. Harvey, Dirk Kalp, Chris McGlone, Jeff McMahill, Michael F. Polis, Jefferey A. Shufelt, and Daniel Yocum. In Proceedings of the DARPA Image Understanding Workshop, pp. 779–812, 1997.
topTech Report
- An Analysis of Stochastic Game Theory for Multiagent Reinforcement Learning. Michael Bowling and Manuela Veloso. Technical report CMU-CS-00-165, Computer Science Department, Carnegie Mellon University, 2000.
topOther
- Multiagent Planning in the Presence of Multiple Goals. Michael Bowling, Rune Jensen, and Manuela Veloso. In Rene Jorna, Wout van Wezel, and Alex Meystel, editors, Planning in Intelligent Systems: Aspects, Motivations, and Methods, Intelligent Series, pp. 345–371, Wiley, 2005.
- Multiagent Learning in the Presence of Agents with Limitations. Michael Bowling. Ph.D. Thesis, Computer Science Department, Carnegie Mellon University, Pittsburgh, PA, 2003. Available as technical report CMU-CS-03-118
topUnspecified
- The Lemonade Stand Game Competition: Solving Unsolvable Games. Martin Zinkevich, Michael Bowling, and Michael Wunder. ACM SIGecom Exchanges, 10(1):35–38, 2011.