Metraipolis › archive › dc_383d5dd41dc6
SpikeCredit: Temporal Credit Carrier for Reinforcement Learning with Sparse Rewards — arXiv:2609.35268
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35268
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:38:59.676Z
- SHA-256 of the archived text
e07cff10690a6b2c6f199f3096eb2007474c15579328e4f429ef0d40721bb3d6- Stable URL of this page
https://metraipolis.com/documento/dc_383d5dd41dc6
How to cite
SpikeCredit: Temporal Credit Carrier for Reinforcement Learning with Sparse Rewards — arXiv:2609.35268 — arXiv (en), https://arxiv.org/abs/2609.35268 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_383d5dd41dc6 (Metraipolis archive dc_383d5dd41dc6, sha256 e07cff10690a6b2c6f199f3096eb2007474c15579328e4f429ef0d40721bb3d6)
BibTeX
@misc{dc383d5dd41dc6,
title = {SpikeCredit: Temporal Credit Carrier for Reinforcement Learning with Sparse Rewards — arXiv:2609.35268},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35268},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_383d5dd41dc6; sha256 e07cff10690a6b2c6f199f3096eb2007474c15579328e4f429ef0d40721bb3d6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35268. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reinforcement learning (RL) with sparse rewards is challenging because delayed outcomes provide little guidance about which intermediate computations caused success or failure. We argue that reliable credit assignment requires policy dynamics that preserve and expose credit-relevant information over time, a role we formalize as Temporal Credit Carriers (TCCs) and that spiking neural networks (SNNs) naturally fulfill through graded membrane traces and event-driven spikes. Based on this hypothesis, we propose SpikeCredit, an SNN-based framework for RL with sparse rewards that first performs task-adaptive TCC selection and then closes the loop between a fast TCC-reading pathway, where self-motion feedback constraint uses local behavior-grounded cues to constrain transition-level credit recovery, and a slow TCC-writing pathway, where credit-targeted trace alignment feeds recovered credit back into the actor to make future TCC dynamics more credit-readable. Across sparse-reward MuJoCo tasks, SpikeCredit improves Last10 return over sparse SNN baselines by +1169% on Ant, +953% on Hopper, +723% on Swimmer, and +1781% on Walker2d, and exceeds the dense-reward baseline on Swimmer by +113%. Mechanistic analyses further show substantially stronger alignment with dense rewards than the sparse SNN baseline. These results position spiking dynamics as credit-preserving substrates for sparse-reward RL. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.35268 — 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 2026-10-07T22:14:28.400Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).