Metraipolis › archive › dc_7776cafe9987

EVOL: Simulator-Guided Evolutionary Expert Synthesis for Deployment-Free Learning Path Recommendation — arXiv:2610.03273

Source
arXiv
Original
https://arxiv.org/abs/2610.03273
License (as archived)
CC0-1.0
Archived
2026-10-05T22:49:34.042Z
SHA-256 of the archived text
5618c54fdb538b59a0a65db4c1cb06b801c9d9785f3cd2b489b7d55d6a28700f
Stable URL of this page
https://metraipolis.com/documento/dc_7776cafe9987

How to cite

EVOL: Simulator-Guided Evolutionary Expert Synthesis for Deployment-Free Learning Path Recommendation — arXiv:2610.03273 — arXiv, https://arxiv.org/abs/2610.03273 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7776cafe9987 (Metraipolis archive dc_7776cafe9987, sha256 5618c54fdb538b59a0a65db4c1cb06b801c9d9785f3cd2b489b7d55d6a28700f)
BibTeX
@misc{dc7776cafe9987,
  title = {EVOL: Simulator-Guided Evolutionary Expert Synthesis for Deployment-Free Learning Path Recommendation — arXiv:2610.03273},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03273},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7776cafe9987; sha256 5618c54fdb538b59a0a65db4c1cb06b801c9d9785f3cd2b489b7d55d6a28700f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03273. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reinforcement learning (RL) for learning path recommendation (LPR) faces two coupled obstacles. First, the policy must commit to a sequence of L concepts without intermediate feedback, producing a combinatorial search space that grows super-exponentially with L and provides reward only at the final step. Second, expert learning paths would be the natural cure for sparse-reward RL, but they do not exist in educational data, because student logs record what learners did, not what they should have done. We address both obstacles by importing a recipe from simulator-based demonstration learning in robotics: the knowledge tracing simulator is used both to synthesize per-learner expert demonstrations through evolutionary search and to train a deployment-free policy that distills these demonstrations into a feed-forward learner. Our framework, EVOL, instantiates this pipeline with an asymmetric actor-critic where the actor commits to deployment-realistic blind planning while the critic exploits the privileged simulator state during training. Across three datasets (ASSIST15, Junyi, and EdNet; 39-189 concepts) and path lengths L = 5, 10, and 20, EVOL surpasses 8 baselines spanning heuristic, sequential, RL, graph-enhanced RL, and LLM-enhanced methods. We further compare three imitation strategies (BC, AWR, and DAPG) and show that final performance is governed by the quality of evolutionary experts rather than by the particular imitation objective.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.03273 — 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 2026-10-05T22:45:55.684Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).