List of works - David Silver

A Monte-Carlo AIXI Approximation

A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning ⬇️

scientific article published in January 2017

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

scientific article published in Science

Bayes-Adaptive Simulation-based Search with Value Function Approximation ⬇️

scientific article published in January 2014

Bootstrapping from Game Tree Search ⬇️

scientific article published in January 2009

Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation ⬇️

scientific article published in January 2009

Discovering faster matrix multiplication algorithms with reinforcement learning

scientific article published on 5 October 2022

Discovery of Useful Questions as Auxiliary Tasks ⬇️

Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search ⬇️

scientific article published in January 2012

Grandmaster level in StarCraft II using multi-agent reinforcement learning

scientific article published on 30 October 2019

Highly accurate protein structure prediction with AlphaFold

scientific article

Human-level control through deep reinforcement learning

scientific article

Imagination-Augmented Agents for Deep Reinforcement Learning ⬇️

scientific article published in January 2017

Learning Continuous Control Policies by Stochastic Value Gradients ⬇️

scientific article published in January 2015

Learning values across many orders of magnitude ⬇️

scientific article published in January 2016

Mastering Atari, Go, chess and shogi by planning with a learned model

scientific article published on 23 December 2020

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

scientific article published on 5 December 2017

Mastering the game of Go with deep neural networks and tree search

scientific article (publication date: 27 January 2016)

Mastering the game of Go without human knowledge ⬇️

scientific article

Mastering the game of Stratego with model-free multiagent reinforcement learning

scientific article published on 2 December 2022

Meta-Gradient Reinforcement Learning ⬇️

scholarly article by Zhongwen Xu et al published 2018 in Advances in Neural Information Processing Systems 31

Monte-Carlo Planning in Large POMDPs ⬇️

Natural Value Approximators: Learning when to Trust Past Estimates ⬇️

scientific article published in January 2017

Successor Features for Transfer in Reinforcement Learning ⬇️

scientific article published in January 2017

The Option Keyboard: Combining Skills in Reinforcement Learning ⬇️

scholarly article by Andre Barreto et al published 2019 in Advances in Neural Information Processing Systems 32

List of works by David Silver

A Monte-Carlo AIXI Approximation

A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning ⬇️

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

Bayes-Adaptive Simulation-based Search with Value Function Approximation ⬇️

Bootstrapping from Game Tree Search ⬇️

Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation ⬇️

Discovering faster matrix multiplication algorithms with reinforcement learning

Discovery of Useful Questions as Auxiliary Tasks ⬇️

Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search ⬇️

Grandmaster level in StarCraft II using multi-agent reinforcement learning

Highly accurate protein structure prediction with AlphaFold

Human-level control through deep reinforcement learning

Imagination-Augmented Agents for Deep Reinforcement Learning ⬇️

Learning Continuous Control Policies by Stochastic Value Gradients ⬇️

Learning values across many orders of magnitude ⬇️

Mastering Atari, Go, chess and shogi by planning with a learned model

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

Mastering the game of Go with deep neural networks and tree search

Mastering the game of Go without human knowledge ⬇️

Mastering the game of Stratego with model-free multiagent reinforcement learning

Meta-Gradient Reinforcement Learning ⬇️

Monte-Carlo Planning in Large POMDPs ⬇️

Natural Value Approximators: Learning when to Trust Past Estimates ⬇️

Successor Features for Transfer in Reinforcement Learning ⬇️

The Option Keyboard: Combining Skills in Reinforcement Learning ⬇️