Research map / Reinforcement learning / Visual and representation RL
Metric Residual Network for Sample Efficient Goal-Conditioned Reinforcement Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use MRN instead of the baseline critic architectures | DDPG+HER · 12 standard GCRL benchmark environments | success rate | Helped |
| Use only the symmetric metric component (ablation) | MRN · GCRL benchmark environments | sample efficiency | Hurt |
| Use only the asymmetric residual component (ablation) | MRN · GCRL benchmark environments | sample efficiency | Hurt |
| Add the symmetric metric component to an asymmetric-only network (ablation) | MRN · GCRL benchmark environments | sample efficiency | Helped |
| Add the asymmetric residual component to a symmetric-only network (ablation) | MRN · GCRL benchmark environments | final performance | Helped |
| Feed state, action, and goal to the second encoder e2 (ablation) | MRN · GCRL benchmark environments | sample efficiency | Hurt |
Closest papers by meaning
- Flattening Hierarchies with Policy Bootstrapping (NeurIPS 2025 · similarity 0.88)
- Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations (NeurIPS 2025 · similarity 0.87)
- OGBench: Benchmarking Offline Goal-Conditioned RL (ICLR 2025 · similarity 0.87)
- Improving the Continuity of Goal-Achievement Ability via Policy Self-Regularization for Goal-Conditioned Reinforcement Learning (ICML 2025 · similarity 0.87)
- Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes (AAAI 2025 · similarity 0.87)
- Score Models for Offline Goal-Conditioned Reinforcement Learning (ICLR 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.