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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add R2R2 regularization | TD7 · 11 envs, UTD=20 | normalized score: 1.02 -> 1.24 | Improved |
| add R2R2 regularization | TD7 · DMC-Hard, UTD=20 | normalized score: 1.02 -> 1.32 | Improved |
| add R2R2 regularization | TD7 · 11 envs, UTD=1 | normalized score: 1.00 -> 1.06 | Improved |
| add R2R2 regularization | Minimalist phi · 11 envs, UTD=20 | normalized score: 5.28 -> 6.20 | Improved |
| add R2R2 regularization | Minimalist phi · Gym MuJoCo, UTD=20 | normalized score: 0.41 -> 0.57 | Improved |
| add R2R2 regularization | Minimalist phi · 11 envs, UTD=1 | normalized score: 1.00 -> 2.74 | Improved |
| add R2R2 regularization | TD7+LN · 11 envs, UTD=20 | normalized score: 0.88 -> 1.10 | Improved |
| add SPL module | SimbaV2 · 11 envs, UTD=20 | normalized score: 1.20 -> 1.34 | Improved |
| add R2R2 regularization | SimbaV2-SPL · 11 envs, UTD=20 | normalized score: 1.34 -> 1.38 | Improved |
| add R2R2 regularization | SimbaV2-SPL · Gym MuJoCo, UTD=20 | normalized score: 1.10 -> 1.08 | No clear effect |
| add zero-centering constraint to the redundancy term (ablation) | R2R2 · Dog-Trot, UTD=20 | return | Hurt |
| add variance preservation loss term (ablation) | R2R2 · Dog-Trot, UTD=20 | return | Improved |
Closest papers by meaning
- Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate (NeurIPS 2024 · similarity 0.87)
- Bridging State and History Representations: Understanding Self-Predictive RL (ICLR 2024 · similarity 0.87)
- Foundation Policies with Hilbert Representations (ICML 2024 · similarity 0.87)
- Dual RL: Unification and New Methods for Reinforcement and Imitation Learning (ICLR 2024 · similarity 0.87)
- Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data (ICLR 2024 · similarity 0.87)
- The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
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.
