Research map / Reinforcement learning / Visual and representation RL
ELDEN: Exploration via Local Dependencies
Zizhao Wang, Jiaheng Hu, Peter Stone, Roberto Martín-Martín
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 |
|---|---|---|---|
| ELDEN vs pCMI dependency detection | ELDEN · Thawing, CarWash, Kitchen | ROC AUC: 0.55 -> 0.71 (Thawing) | Improved |
| ELDEN vs pCMI dependency detection | ELDEN · CarWash | F1: 0.78 -> 0.66 | Hurt |
| ELDEN vs attention score baseline | ELDEN · Thawing | F1: 0.63 -> 0.57 | Hurt |
| Add partial derivative regularization (lambda=1e-2 vs 0) (ablation) | ELDEN · Thawing | ROC AUC: 0.57 -> 0.71 | Improved |
| Add partial derivative regularization (lambda=1e-3 vs 0) (ablation) | ELDEN · CarWash | ROC AUC: 0.54 -> 0.78 | Improved |
| Add partial derivative regularization (lambda=1e-4 vs 0) (ablation) | ELDEN · Kitchen | ROC AUC: 0.64 -> 0.66 | Mixed |
| Too-large regularization coefficient lambda=1e-1 (ablation) | ELDEN · Kitchen | F1: 0.24 -> 0.14 | Hurt |
| Add Mixup for discrete inputs (vs no Mixup, no Reg) (ablation) | ELDEN · CarWash | ROC AUC: 0.44 -> 0.54 | Improved |
| Add Mixup for discrete inputs (vs no Mixup, no Reg) (ablation) | ELDEN · Thawing | ROC AUC: 0.48 -> 0.57 | Improved |
| Add sample prioritization in dynamics learning (ablation) | ELDEN · Kitchen | normalized stage count | Improved |
| Use pCMI instead of partial derivatives for dependencies (ablation) | ELDEN · Kitchen | normalized stage count | No clear effect |
| Inappropriate partial derivative threshold epsilon (ablation) | ELDEN · CarWash | normalized stage count | Hurt |
Closest papers by meaning
- DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.90)
- Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration (NeurIPS 2026 · similarity 0.89)
- Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning (ICML 2024 · similarity 0.89)
- Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
- Action-Dependent Optimality-Preserving Reward Shaping (ICML 2025 · similarity 0.88)
- Imagine, Initialize, and Explore: An Effective Exploration Method in Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.88)
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.
