Metraipolis › archive › dc_315f032e0865

Marginal Coverage Credit Reduces Redundant Exploration in Parallel State-Entropy Optimization — arXiv:2608.27507

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27507
License (as archived)
CC0-1.0
Archived
2026-10-17T10:47:46.906Z
SHA-256 of the archived text
3d66376b786b95a521e0ee664e5c2025778275b7eaccd202758412b8efe037dc
Stable URL of this page
https://metraipolis.com/documento/dc_315f032e0865

How to cite

Marginal Coverage Credit Reduces Redundant Exploration in Parallel State-Entropy Optimization — arXiv:2608.27507 — arXiv (en), https://arxiv.org/abs/2608.27507 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_315f032e0865 (Metraipolis archive dc_315f032e0865, sha256 3d66376b786b95a521e0ee664e5c2025778275b7eaccd202758412b8efe037dc)
BibTeX
@misc{dc315f032e0865,
  title = {Marginal Coverage Credit Reduces Redundant Exploration in Parallel State-Entropy Optimization — arXiv:2608.27507},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27507},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_315f032e0865; sha256 3d66376b786b95a521e0ee664e5c2025778275b7eaccd202758412b8efe037dc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27507. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Policy Gradient for Parallel State Entropy maximization (PGPSE) expands state-space coverage by training independently parameterized policies in replicated copies of the same environment. However, its pooled team-entropy score measures only collective exploration and cannot identify policies that contribute non-redundant coverage. We introduce Marginal Coverage Credit for PGPSE (MCC-PGPSE), which combines leave-one-policy-out coverage with state-owner specialization to estimate policy-specific credit. MCC-PGPSE preserves PGPSE's pooled objective and redistributes non-negative auxiliary intrinsic rewards according to these credits without changing their total mass. This redistribution is designed to discourage redundant visitation and promote complementary coverage. We evaluated MCC-PGPSE in controlled environments, seven public discrete-state benchmarks, and representative Room and Maze settings from the original PGPSE protocol. Across all tested settings, MCC-PGPSE produced positive final window gains in normalized team state entropy and state support over the Entropy baseline. Controlled-task comparisons and the fixed-suite public aggregate were significant, whereas five-seed original-protocol comparisons were directionally consistent. Ablations and credit alignment controls indicate that most gains arise from leave-one-policy-out coverage rather than non-uniform weighting, mismatched credit, or neural novelty alone. These results support contribution-conditioned auxiliary reward allocation as an interpretable approach to improving complementary coverage among parallel policies in discrete state spaces.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.27507 — 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 2026-10-17T10:33:42.446Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).