| 2021 | ICML | Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot. | Joel Z. Leibo, Edgar A. Duez-Guzmn, Alexander Vezhnevets, John P. Agapiou, Peter Sunehag, Raphael Koster, Jayd Matyas, Charlie Beattie, Igor Mordatch, Thore Graepel |
| 2014 | ACML | Reinforcement learning with value advice. | Mayank Daswani, Peter Sunehag, Marcus Hutter |
| 2014 | CogSci | A Dual Process Theory of Optimistic Cognition. | Peter Sunehag, Marcus Hutter |
| 2013 | ACML | Q-learning for history-based reinforcement learning. | Mayank Daswani, Peter Sunehag, Marcus Hutter |
| 2013 | ALT | Concentration and Confidence for Discrete Bayesian Sequence Predictors. | Tor Lattimore, Marcus Hutter, Peter Sunehag |
| 2013 | ICML | The Sample-Complexity of General Reinforcement Learning. | Tor Lattimore, Marcus Hutter, Peter Sunehag |
| 2012 | AAAI | Context Tree Maximizing. | Phuong Nguyen, Peter Sunehag, Marcus Hutter |
| 2012 | AusDM | Coding of Non-Stationary Sources as a Foundation for Detecting Change Points and Outliers in Binary Time-Series. | Peter Sunehag, Wen Shao, Marcus Hutter |
| 2012 | DCC | Adaptive Context Tree Weighting. | Alexander O'Neill, Marcus Hutter, Wen Shao, Peter Sunehag |
| 2011 | ALT | Axioms for Rational Reinforcement Learning. | Peter Sunehag, Marcus Hutter |
| 2010 | ALT | Consistency of Feature Markov Processes. | Peter Sunehag, Marcus Hutter |
| 2009 | ICDM | Semi-Markov kMeans Clustering and Activity Recognition from Body-Worn Sensors. | Matthew W. Robards, Peter Sunehag |