output
20192024
most citedRevisiting Fundamentals of Experience Replay

81 citations

Showing 2020Show all

5 papers · 1 filter

cs.CV20202 cited

Visual Concept Reasoning Networks

Taesup Kim, Sungwoong Kim, Yoshua Bengio

A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. It approximates sparsely connec…

cs.LG202081 cited

Revisiting Fundamentals of Experience Replay

William Fedus, Prajit Ramachandran, Rishabh Agarwal +4

Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding. We therefore present a systematic…

q-bio.NC202014 cited

A zero-inflated gamma model for deconvolved calcium imaging traces

Xue-Xin Wei, Ding Zhou, Andres Grosmark +6

Calcium imaging is a critical tool for measuring the activity of large neural populations. Much effort has been devoted to developing "pre-processing" tools for calcium video data,…

stat.ML202049 cited

GenDICE: Generalized Offline Estimation of Stationary Values

Ruiyi Zhang, Bo Dai, Lihong Li +1

An important problem that arises in reinforcement learning and Monte Carlo methods is estimating quantities defined by the stationary distribution of a Markov chain. In many real-w…

cs.LG20201 cited

Cut-Based Graph Learning Networks to Discover Compositional Structure of Sequential Video Data

Kyoung-Woon On, Eun-Sol Kim, Yu-Jung Heo +1

Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However,…