activity
20172022
most citedRainbow: Combining Improvements in Deep Reinforcement Learning

424 citations · 1.3k across the 16 of their papers we have counts for

collaborators
Showing 2018Show all

5 papers · 1 filter

cs.LG2018

Implicit Quantile Networks for Distributional Reinforcement Learning

Will Dabney, Georg Ostrovski, David Silver +1

In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN. We…

cs.LG2018

Autoregressive Quantile Networks for Generative Modeling

Georg Ostrovski, Will Dabney, Rémi Munos

We introduce autoregressive implicit quantile networks (AIQN), a fundamentally different approach to generative modeling than those commonly used, that implicitly captures the dist…

cs.LG2018

Low-pass Recurrent Neural Networks - A memory architecture for longer-term correlation discovery

Thomas Stepleton, Razvan Pascanu, Will Dabney +3

Reinforcement learning (RL) agents performing complex tasks must be able to remember observations and actions across sizable time intervals. This is especially true during the init…

cs.LG2018

Distributed Distributional Deterministic Policy Gradients

Gabriel Barth-Maron, Matthew W. Hoffman, David Budden +6

This work adopts the very successful distributional perspective on reinforcement learning and adapts it to the continuous control setting. We combine this within a distributed fram…

stat.ML2018

An Analysis of Categorical Distributional Reinforcement Learning

Mark Rowland, Marc G. Bellemare, Will Dabney +2

Distributional approaches to value-based reinforcement learning model the entire distribution of returns, rather than just their expected values, and have recently been shown to yi…