Metraipolis › archive › dc_09ed98b0cd5f
GEM-MPC: Balancing Exploration and Exploitation through Expert-Guided Planning — arXiv:2609.21735
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.21735
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T01:45:12.048Z
- SHA-256 of the archived text
01700267b83003c0b4007641e430a1f6429af2b79212a0df3d48e145c4e8b208- Stable URL of this page
https://metraipolis.com/documento/dc_09ed98b0cd5f
How to cite
GEM-MPC: Balancing Exploration and Exploitation through Expert-Guided Planning — arXiv:2609.21735 — arXiv (en), https://arxiv.org/abs/2609.21735 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09ed98b0cd5f (Metraipolis archive dc_09ed98b0cd5f, sha256 01700267b83003c0b4007641e430a1f6429af2b79212a0df3d48e145c4e8b208)
BibTeX
@misc{dc09ed98b0cd5f,
title = {GEM-MPC: Balancing Exploration and Exploitation through Expert-Guided Planning — arXiv:2609.21735},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.21735},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09ed98b0cd5f; sha256 01700267b83003c0b4007641e430a1f6429af2b79212a0df3d48e145c4e8b208},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21735. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Effective exploration in high-dimensional continuous control remains a central challenge in reinforcement learning. Planning-based methods address this by combining online planning with learned policies and value functions, but their components can become misaligned during training: learned sampling policies may diverge from planner behavior, while planning distributions stored in replay become stale as the model and value function evolve. Reanalysis can refresh these targets, but at substantial computational cost. We propose GEM-MPC, an MPPI-based reinforcement learning method that improves the interaction between planning and learning. GEM-MPC uses MPPI to combine a policy trained to clone the planner with a KL-regularized policy that explores around it, providing complementary exploitation and guided exploration within planning. We further introduce Gated Prior Distillation, which selectively learns from stored planning distributions only when they provide a better target than the current prior, reducing the impact of stale planning data without requiring full reanalysis. Across continuous-control benchmarks, GEM-MPC consistently outperforms existing planning-based baselines under lower computational budgets. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.21735 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T01:14:16.646Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).