Marc G. Bellemare

research

∙ 05/28/2023

The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation

We study the problem of temporal-difference-based policy evaluation in r...

0 Mark Rowland, et al. ∙

research

∙ 04/25/2023

Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks

Auxiliary tasks improve the representations learned by deep reinforcemen...

0 Jesse Farebrother, et al. ∙

research

∙ 01/11/2023

An Analysis of Quantile Temporal-Difference Learning

We analyse quantile temporal-difference learning (QTD), a distributional...

0 Mark Rowland, et al. ∙

research

∙ 12/08/2022

A Novel Stochastic Gradient Descent Algorithm for Learning Principal Subspaces

Many machine learning problems encode their data as a matrix with a poss...

0 Charline Le Lan, et al. ∙

research

∙ 07/15/2022

The Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning

We study the multi-step off-policy learning approach to distributional R...

0 Yunhao Tang, et al. ∙

research

∙ 06/03/2022

Beyond Tabula Rasa: Reincarnating Reinforcement Learning

Learning tabula rasa, that is without any prior knowledge, is the preval...

0 Rishabh Agarwal, et al. ∙

research

∙ 05/24/2022

Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning

Continuous-time reinforcement learning offers an appealing formalism for...

0 Harley Wiltzer, et al. ∙

research

∙ 03/01/2022

On the Generalization of Representations in Reinforcement Learning

In reinforcement learning, state representations are used to tractably d...

66 Charline Le Lan, et al. ∙

research

∙ 09/22/2021

On Bonus-Based Exploration Methods in the Arcade Learning Environment

Research on exploration in reinforcement learning, as applied to Atari 2...

0 Adrien Ali Taïga, et al. ∙

research

∙ 08/30/2021

Deep Reinforcement Learning at the Edge of the Statistical Precipice

Deep reinforcement learning (RL) algorithms are predominantly evaluated ...

0 Rishabh Agarwal, et al. ∙

research

∙ 02/02/2021

Metrics and continuity in reinforcement learning

In most practical applications of reinforcement learning, it is untenabl...

10 Charline Le Lan, et al. ∙

research

∙ 01/13/2021

Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning

Reinforcement learning methods trained on few environments rarely learn ...

21 Rishabh Agarwal, et al. ∙

research

∙ 09/15/2020

The Importance of Pessimism in Fixed-Dataset Policy Optimization

We study worst-case guarantees on the expected return of fixed-dataset p...

4 Jacob Buckman, et al. ∙

research

∙ 07/10/2020

Representations for Stable Off-Policy Reinforcement Learning

Reinforcement learning with function approximation can be unstable and e...

14 Dibya Ghosh, et al. ∙

research

∙ 03/27/2020

A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms

We present a distributional approach to theoretical analyses of reinforc...

6 Philip Amortila, et al. ∙

research

∙ 03/09/2020

Zooming for Efficient Model-Free Reinforcement Learning in Metric Spaces

Despite the wealth of research into provably efficient reinforcement lea...

8 Ahmed Touati, et al. ∙

research

∙ 02/28/2020

On Catastrophic Interference in Atari 2600 Games

Model-free deep reinforcement learning algorithms are troubled with poor...

8 William Fedus, et al. ∙

research

∙ 11/28/2019

Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction

Text-based games are a natural challenge domain for deep reinforcement l...

3 Vishal Jain, et al. ∙

research

∙ 08/06/2019

Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment

This paper provides an empirical evaluation of recently developed explor...

2 Adrien Ali Taïga, et al. ∙

research

∙ 06/06/2019

DeepMDP: Learning Continuous Latent Space Models for Representation Learning

Many reinforcement learning (RL) tasks provide the agent with high-dimen...

4 Carles Gelada, et al. ∙

research

∙ 02/21/2019

Statistics and Samples in Distributional Reinforcement Learning

We present a unifying framework for designing and analysing distribution...

64 Mark Rowland, et al. ∙

research

∙ 02/19/2019

Hyperbolic Discounting and Learning over Multiple Horizons

Reinforcement learning (RL) typically defines a discount factor as part ...

4 William Fedus, et al. ∙

research

∙ 02/08/2019

Distributional reinforcement learning with linear function approximation

Despite many algorithmic advances, our theoretical understanding of prac...

18 Marc G. Bellemare, et al. ∙

research

∙ 02/01/2019

The Hanabi Challenge: A New Frontier for AI Research

From the early days of computing, games have been important testbeds for...

54 Nolan Bard, et al. ∙

research

∙ 01/31/2019

A Geometric Perspective on Optimal Representations for Reinforcement Learning

This paper proposes a new approach to representation learning based on g...

10 Marc G. Bellemare, et al. ∙

research

∙ 01/31/2019

Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue

We consider the problem of designing an artificial agent capable of inte...

8 Kory W. Mathewson, et al. ∙

research

∙ 01/31/2019

The Value Function Polytope in Reinforcement Learning

We establish geometric and topological properties of the space of value ...

10 Robert Dadashi, et al. ∙

research

∙ 01/30/2019

A Comparative Analysis of Expected and Distributional Reinforcement Learning

Since their introduction a year ago, distributional approaches to reinfo...

6 Clare Lyle, et al. ∙

research

∙ 01/27/2019

Off-Policy Deep Reinforcement Learning by Bootstrapping the Covariate Shift

In this paper we revisit the method of off-policy corrections for reinfo...

14 Carles Gelada, et al. ∙

research

∙ 12/14/2018

Dopamine: A Research Framework for Deep Reinforcement Learning

Deep reinforcement learning (deep RL) research has grown significantly i...

1 Pablo Samuel Castro, et al. ∙

research

∙ 11/30/2018

An Introduction to Deep Reinforcement Learning

Deep reinforcement learning is the combination of reinforcement learning...

28 Vincent Francois-Lavet, et al. ∙

research

∙ 08/29/2018

Approximate Exploration through State Abstraction

Although exploration in reinforcement learning is well understood from a...

2 Adrien Ali Taïga, et al. ∙

research

∙ 07/31/2018

Count-Based Exploration with the Successor Representation

The problem of exploration in reinforcement learning is well-understood ...

4 Marlos C. Machado, et al. ∙

research

∙ 02/22/2018

An Analysis of Categorical Distributional Reinforcement Learning

Distributional approaches to value-based reinforcement learning model th...

0 Mark Rowland, et al. ∙

research

∙ 10/27/2017

Distributional Reinforcement Learning with Quantile Regression

In reinforcement learning an agent interacts with the environment by tak...

0 Will Dabney, et al. ∙

research

∙ 07/21/2017

A Distributional Perspective on Reinforcement Learning

In this paper we argue for the fundamental importance of the value distr...

0 Marc G. Bellemare, et al. ∙

research

∙ 05/30/2017

The Cramer Distance as a Solution to Biased Wasserstein Gradients

The Wasserstein probability metric has received much attention from the ...

0 Marc G. Bellemare, et al. ∙

research

∙ 04/15/2017

The Reactor: A Sample-Efficient Actor-Critic Architecture

In this work we present a new reinforcement learning agent, called React...

0 Audrūnas Gruslys, et al. ∙

research

∙ 04/10/2017

Automated Curriculum Learning for Neural Networks

We introduce a method for automatically selecting the path, or syllabus,...

0 Alex Graves, et al. ∙

research

∙ 06/08/2016

Safe and Efficient Off-Policy Reinforcement Learning

In this work, we take a fresh look at some old and new algorithms for of...

0 Remi Munos, et al. ∙

research

∙ 06/06/2016

Unifying Count-Based Exploration and Intrinsic Motivation

We consider an agent's uncertainty about its environment and the problem...

0 Marc G. Bellemare, et al. ∙

research

∙ 02/16/2016

Q(λ) with Off-Policy Corrections

We propose and analyze an alternate approach to off-policy multi-step te...

0 Anna Harutyunyan, et al. ∙

research

∙ 12/15/2015

Increasing the Action Gap: New Operators for Reinforcement Learning

This paper introduces new optimality-preserving operators on Q-functions...

0 Marc G. Bellemare, et al. ∙

research

∙ 11/19/2014

Compress and Control

This paper describes a new information-theoretic policy evaluation techn...

0 Joel Veness, et al. ∙

research

∙ 07/19/2012

The Arcade Learning Environment: An Evaluation Platform for General Agents

In this article we introduce the Arcade Learning Environment (ALE): both...

0 Marc G. Bellemare, et al. ∙

Marc G. Bellemare

Featured Co-authors