Research map / Reinforcement learning / Visual and representation RL
Return-Based Contrastive Representation Learning for Reinforcement Learning
Guoqing Liu, Chuheng Zhang, Li Zhao, Tao Qin, Jinhua Zhu, Li Jian, Nenghai Yu, Tie-Yan Liu
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 the RCRL auxiliary task instead of using CURL | Rainbow · Training | additional training time: 21\% vs 30\% | Improved |
| Use segment-based sampling instead of direct Z-learning sampling | RCRL · Alien | positive-to-negative sample ratio: 2:8 -> 1:1 | Improved |
| Use return-based representations with poorly or sparsely defined rewards | RCRL · Reinforcement learning tasks | task performance | Hurt |
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.
- CURL — CURL: Contrastive Unsupervised Representations for Reinforcement Learning (ICML 2020) · better on 1 of 1 shared result
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
- Contrastive Learning as Goal-Conditioned Reinforcement Learning (NeurIPS 2022 · similarity 0.90)
- Reinforcement Learning with Automated Auxiliary Loss Search (NeurIPS 2022 · similarity 0.89)
- Learning State Representations from Random Deep Action-conditional Predictions (NeurIPS 2021 · similarity 0.88)
- Return-Critic: Bridging Goal Discrepancy for Efficient Visual Reinforcement Learning (ICML 2026 · similarity 0.88)
- ContraDiff: Planning Towards High Return States via Contrastive Learning (ICLR 2025 · similarity 0.87)
- Representation Learning Enables Scalable Multitask Deep Reinforcement Learning (NeurIPS 2026 · similarity 0.86)
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.
