Research map / Reinforcement learning / Visual and representation RL
Covariance Volume Maximization for Embodied Latent Exploration in Deep Reinforcement Learning
Yiming Wang, Yiheng Zhang, Kaiyan Zhao, Xingjie Zuo, Xingyu Liu, Xuetao Li, Furui Liu, Bo An, Leong Hou U
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 policy-mixture training of behavioral encoder (ablation) | CVM · Nav-hard and Targeted Handover | success rate | Improved |
| use behavioral-metric encoder instead of dynamics-based or temporal-metric encoder (ablation) | CVM · navigation and manipulation tasks | success rate | Improved |
| use volume-expansion bonus instead of latent displacement or directional spanning (ablation) | CVM · harder tasks | success rate | Improved |
| replace baselines with CVM | EME / HILP · Nav-hard | success rate: 45.5% -> 69.2% | Improved |
| CVM vs EME on single-object grasping | EME · Grasp (real robot) | success rate: 82.2% vs 81.2% | No clear effect |
| use CVM bonus without task rewards | CVM · Navigation-medium and Manipulation-medium (unsupervised) | success rate | Improved |
Closest papers by meaning
- Imagine Beyond ! Distributionally Robust Autoencoding for State Space Coverage in Online Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
- Parameter Exploration for RLVR via Variational Learning (NeurIPS 2026 · similarity 0.87)
- DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization (ICLR 2024 · similarity 0.87)
- Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations (ICML 2024 · similarity 0.86)
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024 · similarity 0.86)
- Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning (NeurIPS 2025 · 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.
