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...

6 Julien Perolat, et al. ∙

research

∙ 10/25/2021

Self-Consistent Models and Values

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

6 Gregory Farquhar, et al. ∙

research

∙ 09/09/2021

Bootstrapped Meta-Learning

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

23 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...

2 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 ...

43 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...

0 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...

5 Vivek Veeriah, et al. ∙

research

∙ 07/17/2020

Discovering Reinforcement Learning Algorithms

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

72 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...

9 Zhongwen Xu, et al. ∙

research

∙ 02/28/2020

Self-Tuning Deep Reinforcement Learning

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

20 Tom Zahavy, et al. ∙

research

∙ 02/19/2020

Value-driven Hindsight Modelling

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

17 Arthur Guez, et al. ∙

research

∙ 12/11/2019

What Can Learned Intrinsic Rewards Capture?

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

25 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 ...

23 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...

7 Vivek Veeriah, et al. ∙

research

∙ 08/09/2019

Behaviour Suite for Reinforcement Learning

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

2 Ian Osband, et al. ∙

research

∙ 07/05/2019

On Inductive Biases in Deep Reinforcement Learning

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

6 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...

12 Andre Barreto, et al. ∙

research

∙ 01/11/2019

An investigation of model-free planning

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

10 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...

0 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...

6 Diana Borsa, et al. ∙

research

∙ 12/17/2018

Bayesian Optimization in AlphaGo

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

129 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...

2 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...

0 Will Dabney, et al. ∙

research

∙ 05/24/2018

Meta-Gradient Reinforcement Learning

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

0 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...

0 Greg Wayne, et al. ∙

research

∙ 03/02/2018

Distributed Prioritized Experience Replay

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

0 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...

0 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...

0 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...

0 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 ...

0 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...

0 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...

0 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...

0 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...

0 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 ...

0 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...

0 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...

0 Nicolas Heess, et al. ∙

research

∙ 08/18/2016

Decoupled Neural Interfaces using Synthetic Gradients

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

0 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...

0 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...

0 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 ...

0 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...

0 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 ...

0 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...

0 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...

0 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...

0 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...

0 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...

0 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...

0 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...

0 Volodymyr Mnih, et al. ∙

David Silver

Featured Co-authors