
Learning and Planning in Complex Action Spaces
Many important realworld problems have action spaces that are highdime...
read it

Online and Offline Reinforcement Learning by Planning with a Learned Model
Learning efficiently from small amounts of data has long been the focus ...
read it

Muesli: Combining Improvements in Policy Optimization
We propose a novel policy update that combines regularized policy optimi...
read it

Discovery of Options via MetaLearned Subgoals
Temporal abstractions in the form of options have been shown to help rei...
read it

Discovering Reinforcement Learning Algorithms
Reinforcement learning (RL) algorithms update an agent's parameters acco...
read it

MetaGradient Reinforcement Learning with an Objective Discovered Online
Deep reinforcement learning includes a broad family of algorithms that p...
read it

SelfTuning Deep Reinforcement Learning
Reinforcement learning (RL) algorithms often require expensive manual or...
read it

Valuedriven Hindsight Modelling
Value estimation is a critical component of the reinforcement learning (...
read it

What Can Learned Intrinsic Rewards Capture?
Reinforcement learning agents can include different components, such as ...
read it

Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Constructing agents with planning capabilities has long been one of the ...
read it

Discovery of Useful Questions as Auxiliary Tasks
Arguably, intelligent agents ought to be able to discover their own ques...
read it

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

On Inductive Biases in Deep Reinforcement Learning
Many deep reinforcement learning algorithms contain inductive biases tha...
read it

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...
read it

An investigation of modelfree planning
The field of reinforcement learning (RL) is facing increasingly challeng...
read it

Credit Assignment Techniques in Stochastic Computation Graphs
Stochastic computation graphs (SCGs) provide a formalism to represent st...
read it

Universal Successor Features Approximators
The ability of a reinforcement learning (RL) agent to learn about many r...
read it

Bayesian Optimization in AlphaGo
During the development of AlphaGo, its many hyperparameters were tuned ...
read it

Humanlevel performance in firstperson multiplayer games with populationbased deep reinforcement learning
Recent progress in artificial intelligence through reinforcement learnin...
read it

Implicit Quantile Networks for Distributional Reinforcement Learning
In this work, we build on recent advances in distributional reinforcemen...
read it

MetaGradient Reinforcement Learning
The goal of reinforcement learning algorithms is to estimate and/or opti...
read it

Unsupervised Predictive Memory in a GoalDirected Agent
Animals execute goaldirected behaviours despite the limited range and s...
read it

Distributed Prioritized Experience Replay
We propose a distributed architecture for deep reinforcement learning at...
read it

Unicorn: Continual Learning with a Universal, Offpolicy Agent
Some realworld domains are best characterized as a single task, but for...
read it

Learning to Search with MCTSnets
Planning problems are among the most important and wellstudied problems...
read it

Mastering Chess and Shogi by SelfPlay with a General Reinforcement Learning Algorithm
The game of chess is the most widelystudied domain in the history of ar...
read it

A Unified GameTheoretic Approach to Multiagent Reinforcement Learning
To achieve general intelligence, agents must learn how to interact with ...
read it

Rainbow: Combining Improvements in Deep Reinforcement Learning
The deep reinforcement learning community has made several independent i...
read it

StarCraft II: A New Challenge for Reinforcement Learning
This paper introduces SC2LE (StarCraft II Learning Environment), a reinf...
read it

ImaginationAugmented Agents for Deep Reinforcement Learning
We introduce ImaginationAugmented Agents (I2As), a novel architecture f...
read it

Emergence of Locomotion Behaviours in Rich Environments
The reinforcement learning paradigm allows, in principle, for complex be...
read it

The Predictron: EndToEnd Learning and Planning
One of the key challenges of artificial intelligence is to learn models ...
read it

Reinforcement Learning with Unsupervised Auxiliary Tasks
Deep reinforcement learning agents have achieved stateoftheart result...
read it

Learning and Transfer of Modulated Locomotor Controllers
We study a novel architecture and training procedure for locomotion task...
read it

Decoupled Neural Interfaces using Synthetic Gradients
Training directed neural networks typically requires forwardpropagating...
read it

Successor Features for Transfer in Reinforcement Learning
Transfer in reinforcement learning refers to the notion that generalizat...
read it

Deep Reinforcement Learning from SelfPlay in ImperfectInformation Games
Many realworld applications can be described as largescale games of im...
read it

Learning values across many orders of magnitude
Most learning algorithms are not invariant to the scale of the function ...
read it

Asynchronous Methods for Deep Reinforcement Learning
We propose a conceptually simple and lightweight framework for deep rein...
read it

Learning Continuous Control Policies by Stochastic Value Gradients
We present a unified framework for learning continuous control policies ...
read it

Continuous control with deep reinforcement learning
We adapt the ideas underlying the success of Deep QLearning to the cont...
read it

Massively Parallel Methods for Deep Reinforcement Learning
We present the first massively distributed architecture for deep reinfor...
read it

Value Iteration with Options and State Aggregation
This paper presents a way of solving Markov Decision Processes that comb...
read it

Move Evaluation in Go Using Deep Convolutional Neural Networks
The game of Go is more challenging than other board games, due to the di...
read it

Better Optimism By Bayes: Adaptive Planning with Rich Models
The computational costs of inference and planning have confined Bayesian...
read it

Learning to Win by Reading Manuals in a MonteCarlo Framework
Domain knowledge is crucial for effective performance in autonomous cont...
read it

Playing Atari with Deep Reinforcement Learning
We present the first deep learning model to successfully learn control p...
read it

Efficient BayesAdaptive Reinforcement Learning using SampleBased Search
Bayesian modelbased reinforcement learning is a formally elegant approa...
read it

A Monte Carlo AIXI Approximation
This paper introduces a principled approach for the design of a scalable...
read it