Research map / Reinforcement learning / Visual and representation RL
Mapping State Space using Landmarks for Universal Goal Reaching
Zhiao Huang, Fangchen Liu, Hao Su
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 |
|---|---|---|---|
| use landmark-map planning with a locally trained UVFA instead of HER alone | goal-reaching agent · 2DReach and 2DPush | performance | Improved |
| use landmark-map planning with a locally trained UVFA instead of HER alone | goal-reaching agent · BlockedFetchReach and FetchPush | performance | Improved |
| use landmark-map planning with a locally trained UVFA instead of HER alone | goal-reaching agent · PointMaze and AntMaze | success rate | Improved |
| use landmark-map planning rather than HIRO | goal-reaching agent · Large AntMaze sparse, 2M steps | success rate: 0.0 -> 0.5 | Improved |
| use landmark-map planning rather than HIRO | goal-reaching agent · Large AntMaze dense, 2M steps | success rate: 0.8 -> 0.9 | Improved |
| sample landmarks with farthest point sampling rather than uniform sampling (ablation) | landmark-based planner · fix-start AntMaze | success rate | Improved |
| vary the number of landmarks and edge clipping threshold (ablation) | landmark-based planner · AntMaze | performance | No clear effect |
Closest papers by meaning
- Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning (NeurIPS 2021 · similarity 0.87)
- Learning World Models for Unconstrained Goal Navigation (NeurIPS 2024 · similarity 0.87)
- Model-Based Visual Planning with Self-Supervised Functional Distances (ICLR 2021 · similarity 0.87)
- Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning (NeurIPS 2021 · similarity 0.87)
- PcLast: Discovering Plannable Continuous Latent States (ICML 2024 · similarity 0.86)
- Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning (NeurIPS 2024 · similarity 0.85)
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.
