Research map / Reinforcement learning / Policy gradient and actor-critic
Goal Reaching with Eikonal-Constrained Hierarchical Quasimetric Reinforcement Learning
Vittorio Giammarino, Ahmed H Qureshi
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 hierarchy with Eikonal high-level value (Eik-HiQRL over Eik-QRL) | Eik-QRL · antmaze navigate giant | success rate (%): 8 ± 2 -> 59 ± 7 | Improved |
| add hierarchy with Eikonal high-level value (Eik-HiQRL over Eik-QRL) | Eik-QRL · antmaze stitch large | success rate (%): 23 ± 4 -> 81 ± 8 | Improved |
| add Eikonal PDE constraint (Eik-QRL over QRL) | QRL · antmaze navigate large | success rate (%): 54 ± 9 -> 74 ± 3 | Improved |
| use Eikonal constraint instead of HJB constraint | HJB-QRL · antmaze navigate medium | success rate (%): 31 ± 4 -> 84 ± 3 | Improved |
| add PDE constraints to QRL | QRL · pointmaze giant navigate | collision rate (%): 60 ± 8 -> 18 ± 12 | Improved |
| add PDE constraints to QRL | QRL · pointmaze | success rate (%) | No clear effect |
| add Eikonal-QRL to HIQL high level (Eik-HiQRL over Eik-HIQL) | Eik-HIQL · antsoccer stitch arena | success rate (%): 2 ± 0 -> 32 ± 4 | Improved |
| Eik-HiQRL versus HIQL on stitching soccer | HIQL · antsoccer stitch arena | success rate (%): 17 ± 3 -> 32 ± 4 | Improved |
| Eik-HiQRL versus HIQL on cube manipulation | HIQL · cube-single-play | success rate (%): 31 ± 4 -> 12 ± 3 | Hurt |
| Eik-HiQRL versus HIQL on scene manipulation | HIQL · scene-play | success rate (%): 52 ± 3 -> 55 ± 14 | No clear effect |
| Eik-HiQRL versus QRL on manipulation | QRL · scene-play | success rate (%): 8 ± 2 -> 55 ± 14 | Improved |
| Eik-HiQRL versus best baseline on humanoidmaze large-stitch | best baseline · humanoidmaze large-stitch | success rate: t = 11.7, p ≈ 10^-9 | Improved |
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.
- HIQL — HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023) · better on 4 of 6 shared results
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
- Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations (NeurIPS 2025 · similarity 0.89)
- Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- QPRL : Learning Optimal Policies with Quasi-Potential Functions for Asymmetric Traversal (ICML 2025 · similarity 0.88)
- Conservative Offline Goal-Conditioned Implicit V-Learning (ICML 2025 · similarity 0.88)
- Flattening Hierarchies with Policy Bootstrapping (NeurIPS 2025 · similarity 0.87)
- Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning (NeurIPS 2025 · 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.
