| Outracing champion Gran Turismo drivers with deep reinforcement learning PR Wurman, S Barrett, K Kawamoto, J MacGlashan, K Subramanian, ... Nature 602 (7896), 223-228, 2022 | 672 | 2022 |
| Terahertz conductivity of thin gold films at the metal-insulator percolation transition M Walther, DG Cooke, C Sherstan, M Hajar, MR Freeman, FA Hegmann Physical Review B—Condensed Matter and Materials Physics 76 (12), 125408, 2007 | 577 | 2007 |
| Application of real-time machine learning to myoelectric prosthesis control: A case series in adaptive switching AL Edwards, MR Dawson, JS Hebert, C Sherstan, RS Sutton, KM Chan, ... Prosthetics and orthotics international 40 (5), 573-581, 2016 | 94 | 2016 |
| Development of the Bento Arm: An improved robotic arm for myoelectric training and research MR Dawson, C Sherstan, JP Carey, JS Hebert, PM Pilarski Proc. of MEC 14, 60-64, 2014 | 39 | 2014 |
| Directly Estimating the Variance of the λ-Return Using Temporal-Difference Methods C Sherstan, B Bennett, K Young, DR Ashley, A White, M White, RS Sutton arXiv preprint arXiv:1801.08287, 2018 | 38* | 2018 |
| A collaborative approach to the simultaneous multi-joint control of a prosthetic arm C Sherstan, J Modayil, PM Pilarski 2015 IEEE International Conference on Rehabilitation Robotics (ICORR), 13-18, 2015 | 28 | 2015 |
| Gamma-nets: Generalizing value estimation over timescale C Sherstan, S Dohare, J MacGlashan, J Günther, PM Pilarski Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 5717-5725, 2020 | 25* | 2020 |
| Value function decomposition for iterative design of reinforcement learning agents J MacGlashan, E Archer, A Devlic, T Seno, C Sherstan, P Wurman, ... Advances in Neural Information Processing Systems 35, 12001-12013, 2022 | 14 | 2022 |
| Predictions, surprise, and predictions of surprise in general value function architectures J Günther, A Kearney, MR Dawson, C Sherstan, PM Pilarski AAAI 2018 Fall Symposium on Reasoning and Learning in Real-World Systems for …, 2018 | 13 | 2018 |
| Accelerating learning in constructive predictive frameworks with the successor representation C Sherstan, MC Machado, PM Pilarski 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2018 | 12 | 2018 |
| Introspective agents: Confidence measures for general value functions C Sherstan, A White, MC Machado, PM Pilarski Artificial General Intelligence (AGI), 2016 | 12 | 2016 |
| Representation and general value functions C Sherstan | 9 | 2020 |
| Communicative capital for prosthetic agents PM Pilarski, RS Sutton, KW Mathewson, C Sherstan, ASR Parker, ... arXiv preprint arXiv:1711.03676, 2017 | 8 | 2017 |
| Steps toward knowledgeable neuroprostheses PM Pilarski, C Sherstan 2016 6th IEEE International Conference on Biomedical Robotics and …, 2016 | 8 | 2016 |
| Towards Prosthetic Arms as Wearable Intelligent Robots C Sherstan University of Alberta, 2015 | 8 | 2015 |
| Communicative capital: a key resource for human–machine shared agency and collaborative capacity KW Mathewson, ASR Parker, C Sherstan, AL Edwards, RS Sutton, ... Neural Computing and Applications 35 (23), 16805-16819, 2023 | 6 | 2023 |
| Multilayer General Value Functions for Robotic Prediction and Control C Sherstan, PM Pilarski IROS 2014 Workshop on AI and Robotics, IEEE/RSJ International Conference on …, 2014 | 5 | 2014 |
| Work in Progress: Temporally Extended Auxiliary Tasks C Sherstan, B Kartal, P Hernandez-Leal, ME Taylor arXiv preprint arXiv:2004.00600, 2020 | 1 | 2020 |
| Evaluating Predictive Knowledge A Kearney, A Koop, C Sherstan, J Gunther, RS Sutton, PM Pilarski, ... AAAI Fall Symposium on Reasoning and Learning In Real-World Systems For Long …, 2018 | 1 | 2018 |
| Automated Reward Design for Gran Turismo M Ma, T Seno, K Subramanian, PR Wurman, P Stone, C Sherstan arXiv preprint arXiv:2511.02094, 2025 | | 2025 |
Patrick M. PilarskiProfessor, University of Alberta, Amii (Alberta Machine Intelligence Institute)Verified email at ualberta.ca
