activity
20172021
most citedRainbow: Combining Improvements in Deep Reinforcement Learning

424 citations · 437 across the 5 of their papers we have counts for

collaborators

9 papers

cs.LG20211 cited

The Difficulty of Passive Learning in Deep Reinforcement Learning

Georg Ostrovski, Pablo Samuel Castro, Will Dabney

Learning to act from observational data without active environmental interaction is a well-known challenge in Reinforcement Learning (RL). Recent approaches involve constraints on…

cs.LG2021

Return-based Scaling: Yet Another Normalisation Trick for Deep RL

Tom Schaul, Georg Ostrovski, Iurii Kemaev +1

Scaling issues are mundane yet irritating for practitioners of reinforcement learning. Error scales vary across domains, tasks, and stages of learning; sometimes by many orders of…

cs.LG20212 cited

On The Effect of Auxiliary Tasks on Representation Dynamics

Clare Lyle, Mark Rowland, Georg Ostrovski +1

While auxiliary tasks play a key role in shaping the representations learnt by reinforcement learning agents, much is still unknown about the mechanisms through which this is achie…

cs.LG20202 cited

Temporally-Extended ε-Greedy Exploration

Will Dabney, Georg Ostrovski, André Barreto

Recent work on exploration in reinforcement learning (RL) has led to a series of increasingly complex solutions to the problem. This increase in complexity often comes at the expen…

cs.LG20198 cited

Adapting Behaviour for Learning Progress

Tom Schaul, Diana Borsa, David Ding +4

Determining what experience to generate to best facilitate learning (i.e. exploration) is one of the distinguishing features and open challenges in reinforcement learning. The adve…

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…