WhiRL is a machine learning research group in the Department of Computer Science at the University of Oxford that is focused on reinforcement learning, deep learning, and related topics, with applications in robotics, video games, and information retrieval.
Latest News
Five papers accepted at ICML 2018
All our five submissions for ICML 2018 have just been accepted: DiCE: The Infinitely Differentiable Monte Carlo Estimator Jakob Foerster, Gregory... read more
Video for AAAI-18 oral “Expected Policy Gradients” by K. Ciosek and S. Whiteson.
Our lab member Kamil Ciosek has published a video of his presentation of his recent paper “Expected Policy Gradients”... read more
Paper accepted at ICLR 2018
Our paper “TreeQN and ATreeC: Differentiable Tree Planning for Deep Reinforcement Learning” has been accepted at #ICLR2018 ! Congratulations to... read more
WhiRL members have two papers accepted at AAMAS 2018
We’re happy to announce that WhiRL members have two accepted papers at #AAMAS2018 this year.Learning with Opponent-Learning Awareness Jakob... read more
Wendelin Boehmer joins WhiRL
Wendelin Boehmer has joined WhiRL as a new postdoctoral researcher.read more
Outstanding Student Paper at AAAI-18
Our paper “Counterfactual Multi−Agent Policy Gradients” by Jakob Foerster‚ Gregory Farquhar‚ Triantafyllos Afouras‚ Nantas Nardelli and Shimon Whiteson has... read more
WhiRL members have three papers accepted at AAAI
Whiteson Research Lab members have three papers accepted at AAAI-2018: Counterfactual Multi-Agent Policy GradientsJakob Foerster, Gregory Farquhar, Triantafyllos Afouras, Nantas Nardelli, Shimon WhitesonAlternating Optimisation and Quadrature... read more
WhiRL members have three papers accepted at NIPS
Whiteson Research Lab members have three papers accepted at NIPS-2017: Utile Context Tree Weighting João Messias and Shimon Whiteson End-to-end Differentiable Proving Tim... read more