1.3k citations · 4.8k across the 58 of their papers we have counts for
8 papers · 1 filter
Distributional Reinforcement Learning with Quantile Regression
Will Dabney, Mark Rowland, Marc G. Bellemare +1
In reinforcement learning an agent interacts with the environment by taking actions and observing the next state and reward. When sampled probabilistically, these state transitions…
Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
Marlos C. Machado, Marc G. Bellemare, Erik Talvitie +3
The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games. It support…
A Distributional Perspective on Reinforcement Learning
Marc G. Bellemare, Will Dabney, Rémi Munos
In this paper we argue for the fundamental importance of the value distribution: the distribution of the random return received by a reinforcement learning agent. This is in contra…
The Cramer Distance as a Solution to Biased Wasserstein Gradients
Marc G. Bellemare, Ivo Danihelka, Will Dabney +4
The Wasserstein probability metric has received much attention from the machine learning community. Unlike the Kullback-Leibler divergence, which strictly measures change in probab…
Automated Curriculum Learning for Neural Networks
Alex Graves, Marc G. Bellemare, Jacob Menick +2
We introduce a method for automatically selecting the path, or syllabus, that a neural network follows through a curriculum so as to maximise learning efficiency. A measure of the…
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
Audrunas Gruslys, Will Dabney, Mohammad Gheshlaghi Azar +3
In this work we present a new agent architecture, called Reactor, which combines multiple algorithmic and architectural contributions to produce an agent with higher sample-efficie…
Count-Based Exploration with Neural Density Models
Georg Ostrovski, Marc G. Bellemare, Aaron van den Oord +1
Bellemare et al. (2016) introduced the notion of a pseudo-count, derived from a density model, to generalize count-based exploration to non-tabular reinforcement learning. This pse…
A Laplacian Framework for Option Discovery in Reinforcement Learning
Marlos C. Machado, Marc G. Bellemare, Michael Bowling
Representation learning and option discovery are two of the biggest challenges in reinforcement learning (RL). Proto-value functions (PVFs) are a well-known approach for representa…