| Tighter variational bounds are not necessarily better T Rainforth, A Kosiorek, TA Le, C Maddison, M Igl, F Wood, YW Teh International Conference on Machine Learning, 4277-4285, 2018 | 152 | 2018 |
| Deep variational reinforcement learning for POMDPs M Igl, L Zintgraf, TA Le, F Wood, S Whiteson International Conference on Machine Learning, 2117-2126, 2018 | 147 | 2018 |
| Auto-encoding sequential monte carlo TA Le, M Igl, T Rainforth, T Jin, F Wood arXiv preprint arXiv:1705.10306, 2017 | 128 | 2017 |
| Treeqn and atreec: Differentiable tree-structured models for deep reinforcement learning G Farquhar, T Rocktäschel, M Igl, S Whiteson arXiv preprint arXiv:1710.11417, 2017 | 101 | 2017 |
| Varibad: A very good method for bayes-adaptive deep rl via meta-learning L Zintgraf, K Shiarlis, M Igl, S Schulze, Y Gal, K Hofmann, S Whiteson arXiv preprint arXiv:1910.08348, 2019 | 82 | 2019 |
| Generalization in reinforcement learning with selective noise injection and information bottleneck M Igl, K Ciosek, Y Li, S Tschiatschek, C Zhang, S Devlin, K Hofmann arXiv preprint arXiv:1910.12911, 2019 | 61 | 2019 |
| The impact of non-stationarity on generalisation in deep reinforcement learning M Igl, G Farquhar, J Luketina, W Boehmer, S Whiteson arXiv e-prints, arXiv: 2006.05826, 2020 | 13 | 2020 |
| Transient non-stationarity and generalisation in deep reinforcement learning M Igl, G Farquhar, J Luketina, W Böhmer, S Whiteson arXiv preprint arXiv:2006.05826, 2020 | 9 | 2020 |
| Multitask soft option learning M Igl, A Gambardella, J He, N Nardelli, N Siddharth, W Böhmer, ... Conference on Uncertainty in Artificial Intelligence, 969-978, 2020 | 8 | 2020 |
| My body is a cage: the role of morphology in graph-based incompatible control V Kurin, M Igl, T Rocktäschel, W Boehmer, S Whiteson arXiv preprint arXiv:2010.01856, 2020 | 7 | 2020 |
| Variational task embeddings for fast adapta-tion in deep reinforcement learning L Zintgraf, M Igl, K Shiarlis, A Mahajan, K Hofmann, S Whiteson International Conference on Learning Representations Workshop (ICLRW), 2019 | 6 | 2019 |
| Exploration in approximate hyper-state space for meta reinforcement learning LM Zintgraf, L Feng, C Lu, M Igl, K Hartikainen, K Hofmann, S Whiteson International Conference on Machine Learning, 12991-13001, 2021 | 5 | 2021 |
| Implicit Communication as Minimum Entropy Coupling S Sokota, CS de Witt, M Igl, L Zintgraf, P Torr, S Whiteson, J Foerster arXiv preprint arXiv:2107.08295, 2021 | | 2021 |
| Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing C Blake, V Kurin, M Igl, S Whiteson arXiv preprint arXiv:2103.01009, 2021 | | 2021 |
| VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning L Zintgraf, S Schulze, C Lu, L Feng, M Igl, K Shiarlis, Y Gal, K Hofmann, ... Journal of Machine Learning Research 22 (289), 1-39, 2021 | | 2021 |
| Inductive biases and generalisation for deep reinforcement learning M Igl University of Oxford, 2021 | | 2021 |
| Generalization in Reinforcement Learning with Selective Noise Injection and Information M Igl, K Ciosek, Y Li, S Tschiatschek, C Zhang, S Devlin, K Hofmann | | 2019 |
| Inference and Distillation for Option Learning M Igl, W Boehmer, A Gambardella, PHS Torr, N Nardelli, N Siddharth, ... Workshop on Probabilistic Reinforcement Learning and Structured Control …, 2018 | | 2018 |
| Composition of queries in probabilistic programming languages M Igl | | 2016 |
| Soft Option Transfer J He, M Igl, M Smith, W Boehmer, S Whiteson | | |
Shimon WhitesonProfessor of Computer Science, University of Oxford / Head of Research, Waymo UKVerified email at cs.ox.ac.uk
