David Silver

Bootstrapped Meta-Learning ICLR 2022 Learning by Directional Gradient Descent ICLR 2022 Planning in Stochastic Environments with a Learned Model ICLR 2022 Policy improvement by planning with Gumbel ICLR 2022 Discovery of Options via Meta-Learned Subgoals NeurIPS 2021 Expected Eligibility Traces AAAI 2021 Learning and Planning in Complex Action Spaces ICML 2021 Muesli: Combining Improvements in Policy Optimization ICML 2021 Online and Offline Reinforcement Learning by Planning with a Learned Model NeurIPS 2021 Proper Value Equivalence NeurIPS 2021 Self-Consistent Models and Values NeurIPS 2021 The Value-Improvement Path: Towards Better Representations for Reinforcement Learning AAAI 2021 A Self-Tuning Actor-Critic Algorithm NeurIPS 2020 Behaviour Suite for Reinforcement Learning ICLR 2020 Discovering Reinforcement Learning Algorithms NeurIPS 2020 Meta-Gradient Reinforcement Learning with an Objective Discovered Online NeurIPS 2020 The Value Equivalence Principle for Model-Based Reinforcement Learning NeurIPS 2020 Value-driven Hindsight Modelling NeurIPS 2020 What Can Learned Intrinsic Rewards Capture? ICML 2020 An Investigation of Model-Free Planning ICML 2019 Credit Assignment Techniques in Stochastic Computation Graphs AISTATS 2019 Discovery of Useful Questions as Auxiliary Tasks NeurIPS 2019 The Option Keyboard: Combining Skills in Reinforcement Learning NeurIPS 2019 Universal Successor Features Approximators ICLR 2019 Distributed Prioritized Experience Replay ICLR 2018 Implicit Quantile Networks for Distributional Reinforcement Learning ICML 2018 Learning to search with MCTSnets ICML 2018 Meta-Gradient Reinforcement Learning NeurIPS 2018 Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement ICML 2018 A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning NeurIPS 2017 Decoupled Neural Interfaces using Synthetic Gradients ICML 2017 FeUdal Networks for Hierarchical Reinforcement Learning ICML 2017 Imagination-Augmented Agents for Deep Reinforcement Learning NeurIPS 2017 Natural Value Approximators: Learning when to Trust Past Estimates NeurIPS 2017 Successor Features for Transfer in Reinforcement Learning NeurIPS 2017 The Predictron: End-To-End Learning and Planning ICML 2017 Asynchronous Methods for Deep Reinforcement Learning ICML 2016 Learning values across many orders of magnitude NeurIPS 2016 Fictitious Self-Play in Extensive-Form Games ICML 2015 Learning Continuous Control Policies by Stochastic Value Gradients NeurIPS 2015 Smooth UCT Search in Computer Poker IJCAI 2015 Universal Value Function Approximators ICML 2015 Bayes-Adaptive Simulation-based Search with Value Function Approximation NeurIPS 2014 Deterministic Policy Gradient Algorithms ICML 2014 Concurrent Reinforcement Learning from Customer Interactions ICML 2013 Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search NeurIPS 2012 Learning to Win by Reading Manuals in a Monte-Carlo Framework ACL 2011 Monte-Carlo Planning in Large POMDPs NeurIPS 2010 Bootstrapping from Game Tree Search NeurIPS 2009 Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation NeurIPS 2009 High Performance Outdoor Navigation from Overhead Data using Imitation Learning RSS 2008