b'David Silver'

research

∙ 06/30/2022

Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning

We introduce DeepNash, an autonomous agent capable of learning to play t...

Julien Perolat, et al. ∙

research

∙ 10/25/2021

Self-Consistent Models and Values

Learned models of the environment provide reinforcement learning (RL) ag...

Gregory Farquhar, et al. ∙

research

∙ 09/09/2021

Bootstrapped Meta-Learning

Meta-learning empowers artificial intelligence to increase its efficienc...

Sebastian Flennerhag, et al. ∙

research

∙ 04/13/2021

Learning and Planning in Complex Action Spaces

Many important real-world problems have action spaces that are high-dime...

Thomas Hubert, et al. ∙

research

∙ 04/13/2021

Online and Offline Reinforcement Learning by Planning with a Learned Model

Learning efficiently from small amounts of data has long been the focus ...

Julian Schrittwieser, et al. ∙

research

∙ 04/13/2021

Muesli: Combining Improvements in Policy Optimization

We propose a novel policy update that combines regularized policy optimi...

Matteo Hessel, et al. ∙

research

∙ 02/12/2021

Discovery of Options via Meta-Learned Subgoals

Temporal abstractions in the form of options have been shown to help rei...

Vivek Veeriah, et al. ∙

research

∙ 07/17/2020

Discovering Reinforcement Learning Algorithms

Reinforcement learning (RL) algorithms update an agent's parameters acco...

Junhyuk Oh, et al. ∙

research

∙ 07/16/2020

Meta-Gradient Reinforcement Learning with an Objective Discovered Online

Deep reinforcement learning includes a broad family of algorithms that p...

Zhongwen Xu, et al. ∙

research

∙ 02/28/2020

Self-Tuning Deep Reinforcement Learning

Reinforcement learning (RL) algorithms often require expensive manual or...

Tom Zahavy, et al. ∙

research

∙ 02/19/2020

Value-driven Hindsight Modelling

Value estimation is a critical component of the reinforcement learning (...

Arthur Guez, et al. ∙

research

∙ 12/11/2019

What Can Learned Intrinsic Rewards Capture?

Reinforcement learning agents can include different components, such as ...

Zeyu Zheng, et al. ∙

research

∙ 11/19/2019

Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

Constructing agents with planning capabilities has long been one of the ...

Julian Schrittwieser, et al. ∙

research

∙ 09/10/2019

Discovery of Useful Questions as Auxiliary Tasks

Arguably, intelligent agents ought to be able to discover their own ques...

Vivek Veeriah, et al. ∙

research

∙ 08/09/2019

Behaviour Suite for Reinforcement Learning

This paper introduces the Behaviour Suite for Reinforcement Learning, or...

Ian Osband, et al. ∙

research

∙ 07/05/2019

On Inductive Biases in Deep Reinforcement Learning

Many deep reinforcement learning algorithms contain inductive biases tha...

Matteo Hessel, et al. ∙

research

∙ 01/30/2019

Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement

The ability to transfer skills across tasks has the potential to scale u...

Andre Barreto, et al. ∙

research

∙ 01/11/2019

An investigation of model-free planning

The field of reinforcement learning (RL) is facing increasingly challeng...

Arthur Guez, et al. ∙

research

∙ 01/07/2019

Credit Assignment Techniques in Stochastic Computation Graphs

Stochastic computation graphs (SCGs) provide a formalism to represent st...

Theophane Weber, et al. ∙

research

∙ 12/18/2018

Universal Successor Features Approximators

The ability of a reinforcement learning (RL) agent to learn about many r...

Diana Borsa, et al. ∙

research

∙ 12/17/2018

Bayesian Optimization in AlphaGo

During the development of AlphaGo, its many hyper-parameters were tuned ...

Yutian Chen, et al. ∙

research

∙ 07/03/2018

Human-level performance in first-person multiplayer games with population-based deep reinforcement learning

Recent progress in artificial intelligence through reinforcement learnin...

Max Jaderberg, et al. ∙

research

∙ 06/14/2018

Implicit Quantile Networks for Distributional Reinforcement Learning

In this work, we build on recent advances in distributional reinforcemen...

Will Dabney, et al. ∙

research

∙ 05/24/2018

Meta-Gradient Reinforcement Learning

The goal of reinforcement learning algorithms is to estimate and/or opti...

Zhongwen Xu, et al. ∙

research

∙ 03/28/2018

Unsupervised Predictive Memory in a Goal-Directed Agent

Animals execute goal-directed behaviours despite the limited range and s...

Greg Wayne, et al. ∙

research

∙ 03/02/2018

Distributed Prioritized Experience Replay

We propose a distributed architecture for deep reinforcement learning at...

Dan Horgan, et al. ∙

research

∙ 02/22/2018

Unicorn: Continual Learning with a Universal, Off-policy Agent

Some real-world domains are best characterized as a single task, but for...

Daniel J. Mankowitz, et al. ∙

research

∙ 02/13/2018

Learning to Search with MCTSnets

Planning problems are among the most important and well-studied problems...

Arthur Guez, et al. ∙

research

∙ 12/05/2017

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

The game of chess is the most widely-studied domain in the history of ar...

David Silver, et al. ∙

research

∙ 11/02/2017

A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning

To achieve general intelligence, agents must learn how to interact with ...

Marc Lanctot, et al. ∙

research

∙ 10/06/2017

Rainbow: Combining Improvements in Deep Reinforcement Learning

The deep reinforcement learning community has made several independent i...

Matteo Hessel, et al. ∙

research

∙ 08/16/2017

StarCraft II: A New Challenge for Reinforcement Learning

This paper introduces SC2LE (StarCraft II Learning Environment), a reinf...

Oriol Vinyals, et al. ∙

research

∙ 07/19/2017

Imagination-Augmented Agents for Deep Reinforcement Learning

We introduce Imagination-Augmented Agents (I2As), a novel architecture f...

Theophane Weber, et al. ∙

research

∙ 07/07/2017

Emergence of Locomotion Behaviours in Rich Environments

The reinforcement learning paradigm allows, in principle, for complex be...

Nicolas Heess, et al. ∙

research

∙ 12/28/2016

The Predictron: End-To-End Learning and Planning

One of the key challenges of artificial intelligence is to learn models ...

David Silver, et al. ∙

research

∙ 11/16/2016

Reinforcement Learning with Unsupervised Auxiliary Tasks

Deep reinforcement learning agents have achieved state-of-the-art result...

Max Jaderberg, et al. ∙

research

∙ 10/17/2016

Learning and Transfer of Modulated Locomotor Controllers

We study a novel architecture and training procedure for locomotion task...

Nicolas Heess, et al. ∙

research

∙ 08/18/2016

Decoupled Neural Interfaces using Synthetic Gradients

Training directed neural networks typically requires forward-propagating...

Max Jaderberg, et al. ∙

research

∙ 06/16/2016

Successor Features for Transfer in Reinforcement Learning

Transfer in reinforcement learning refers to the notion that generalizat...

Andre Barreto, et al. ∙

research

∙ 03/03/2016

Deep Reinforcement Learning from Self-Play in Imperfect-Information Games

Many real-world applications can be described as large-scale games of im...

Johannes Heinrich, et al. ∙

research

∙ 02/24/2016

Learning values across many orders of magnitude

Most learning algorithms are not invariant to the scale of the function ...

Hado van Hasselt, et al. ∙

research

∙ 02/04/2016

Asynchronous Methods for Deep Reinforcement Learning

We propose a conceptually simple and lightweight framework for deep rein...

Volodymyr Mnih, et al. ∙

research

∙ 10/30/2015

Learning Continuous Control Policies by Stochastic Value Gradients

We present a unified framework for learning continuous control policies ...

Nicolas Heess, et al. ∙

research

∙ 09/09/2015

Continuous control with deep reinforcement learning

We adapt the ideas underlying the success of Deep Q-Learning to the cont...

Timothy P. Lillicrap, et al. ∙

research

∙ 07/15/2015

Massively Parallel Methods for Deep Reinforcement Learning

We present the first massively distributed architecture for deep reinfor...

Arun Nair, et al. ∙

research

∙ 01/16/2015

Value Iteration with Options and State Aggregation

This paper presents a way of solving Markov Decision Processes that comb...

Kamil Ciosek, et al. ∙

research

∙ 12/20/2014

Move Evaluation in Go Using Deep Convolutional Neural Networks

The game of Go is more challenging than other board games, due to the di...

Chris J. Maddison, et al. ∙

research

∙ 02/09/2014

Better Optimism By Bayes: Adaptive Planning with Rich Models

The computational costs of inference and planning have confined Bayesian...

Arthur Guez, et al. ∙

research

∙ 01/18/2014

Learning to Win by Reading Manuals in a Monte-Carlo Framework

Domain knowledge is crucial for effective performance in autonomous cont...

S. R. K. Branavan, et al. ∙

research

∙ 12/19/2013

Playing Atari with Deep Reinforcement Learning

We present the first deep learning model to successfully learn control p...

Volodymyr Mnih, et al. ∙

David Silver

Featured Co-authors