AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Masked Contrastive Representation Learning for Reinforcement Learning

Jinhua Zhu, Yingce Xia, Lijun Wu, Jiajun Deng, Wengang Zhou, Tao Qin, Tie‐Yan Liu, Houqiang Li

TPAMI 2022 · Reinforcement learning › Visual and representation RL · approach: Robust visual encoders for RL · 76 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add masked contrastive learning with Transformer on top of Eff. Rainbow (M-CURL vs CURL)M-CURL · Atari 100kmedian HNS: 17.5% -> 24.2%Improved
add masked contrastive learning to Efficient RainbowEff. Rainbow · Atari 100kmedian HNS: 16.1% -> 24.2%Improved
use M-CURL instead of CURL on DMControlSAC · DMControl 100k/500kreturn: outperforms CURL on 14 out of 16Improved
feed consecutive sequential inputs to CURL (seq-CURL) instead of random sampling (ablation)CURL · DMControl Hopper-StandreturnHurt
add a Transformer module on the key side (sym-CURL) (ablation)M-CURL · DMControl Hopper-StandreturnHurt
set masked probability to 0.9 instead of 0.5 (ablation)M-CURL · DMControl Hopper-StandreturnHurt
set masked probability to 0.1 instead of 0.5 (ablation)M-CURL · DMControl Hopper-StandreturnHurt
vary sequence length T from 16 to 256 (ablation)M-CURL · DMControl Hopper-StandreturnNo clear effect
increase Transformer layers from 3 to 4 (ablation)M-CURL · DMControl Hopper-StandreturnHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy