AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning

Sanghyeob Song, Donghyeok Lee, Jinsik Kim, Sungroh Yoon

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning · 0 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 R2R2 regularizationTD7 · 11 envs, UTD=20normalized score: 1.02 -> 1.24Improved
add R2R2 regularizationTD7 · DMC-Hard, UTD=20normalized score: 1.02 -> 1.32Improved
add R2R2 regularizationTD7 · 11 envs, UTD=1normalized score: 1.00 -> 1.06Improved
add R2R2 regularizationMinimalist phi · 11 envs, UTD=20normalized score: 5.28 -> 6.20Improved
add R2R2 regularizationMinimalist phi · Gym MuJoCo, UTD=20normalized score: 0.41 -> 0.57Improved
add R2R2 regularizationMinimalist phi · 11 envs, UTD=1normalized score: 1.00 -> 2.74Improved
add R2R2 regularizationTD7+LN · 11 envs, UTD=20normalized score: 0.88 -> 1.10Improved
add SPL moduleSimbaV2 · 11 envs, UTD=20normalized score: 1.20 -> 1.34Improved
add R2R2 regularizationSimbaV2-SPL · 11 envs, UTD=20normalized score: 1.34 -> 1.38Improved
add R2R2 regularizationSimbaV2-SPL · Gym MuJoCo, UTD=20normalized score: 1.10 -> 1.08No clear effect
add zero-centering constraint to the redundancy term (ablation)R2R2 · Dog-Trot, UTD=20returnHurt
add variance preservation loss term (ablation)R2R2 · Dog-Trot, UTD=20returnImproved

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