AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Oracle-Guided Masked Contrastive Reinforcement Learning for Visuomotor Policies

Yuhang Zhang, Jiaping Xiao, Chao Yan, Mir Feroskhan

TPAMI 2026 · Reinforcement learning › Visual and representation RL · approach: Robust visual encoders for RL · 2 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
use linear decay instead of fixed oracle KL coefficient (ablation)OMC-RL · Tree (Hard)success rate (%): 71.0 -> 78.5Improved
use linear decay instead of exponential decay (ablation)OMC-RL · Tree (Hard)success rate (%): 72.5 -> 78.5Improved
use linear decay instead of fixed coefficient (ablation)OMC-RL · Furniture (Easy)success rate (%): 81.5 -> 91.5Improved
use masked temporal contrastive learning instead of consecutive frames in CURL (ablation)CURL · Furniture (Easy)success rate (%): 30.5 -> 72.5Improved
feed consecutive frames to CURL (ablation)CURL · Barrier (Medium)success rate (%): 30.0 -> 0.0Hurt
add masked contrastive plus oracle guidance vs CURLOMC-RL · Barrier (Medium)success rate (%): 30.0 -> 84.5Improved
add oracle teacher (ablation)OMC-RL · Barrier and Tree scenesnavigation metricsImproved
add oracle teacher (ablation)OMC-RL · Furniture (Easy)navigation metricsMixed
add oracle teacher to NPE (ablation)NPE · simulationnavigation metricsImproved
add non-linear projection head (ablation)OMC-RL · simulationnavigation metricsImproved
add non-linear projection head (ablation)CURL · simulationnavigation metricsImproved
add Transformer to key encoder as well (dual) (ablation)OMC-RL · simulationnavigation metricsHurt

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