Metraipolis › archive › dc_f1946d69682f
Common-Mode Errors Limit Low-Timestep Deep Spiking Q-Networks — arXiv:2610.07808
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07808
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:42:39.722Z
- SHA-256 of the archived text
dde02f04b98f5dc6e4f34f817a3351b7703266376d79c4afe0371d91ed3a47ea- Stable URL of this page
https://metraipolis.com/documento/dc_f1946d69682f
How to cite
Common-Mode Errors Limit Low-Timestep Deep Spiking Q-Networks — arXiv:2610.07808 — arXiv (en), https://arxiv.org/abs/2610.07808 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f1946d69682f (Metraipolis archive dc_f1946d69682f, sha256 dde02f04b98f5dc6e4f34f817a3351b7703266376d79c4afe0371d91ed3a47ea)
BibTeX
@misc{dcf1946d69682f,
title = {Common-Mode Errors Limit Low-Timestep Deep Spiking Q-Networks — arXiv:2610.07808},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07808},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f1946d69682f; sha256 dde02f04b98f5dc6e4f34f817a3351b7703266376d79c4afe0371d91ed3a47ea},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07808. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Spiking neural networks (SNNs) offer sparse and event-driven computation, making them attractive for energy-constrained reinforcement learning (RL) on edge devices. In value-based RL, deep spiking Q-networks (DSQNs) combine such efficiency with action-value estimation for decision making. However, existing DSQNs often require multiple simulation timesteps for competitive performance, increasing computational and energy costs, whereas reducing the timesteps can cause substantial performance degradation. We investigate this degradation from the perspective of Q-value estimation errors. By decomposing errors across actions into common-mode and differential-mode components, we find that low-timestep DSQNs suffer disproportionately from common-mode errors shared across action values, which are particularly detrimental to temporal-difference learning through bootstrapped targets. Based on this finding, we propose Common-Mode Compensation Deep Spiking Q-Network (CMC-DSQN), which uses an auxiliary ANN to compensate for common-mode errors in the SNN outputs. At inference, greedy action selection can be performed directly from the SNN outputs, allowing the auxiliary ANN to be completely removed and preserving the energy efficiency of SNNs. Extensive experiments on Atari and MiniAtar environments demonstrate substantial performance improvements under low-timestep settings. CMC-DSQN outperforms state-of-the-art DSQN baselines by nearly $20\%$ at $T=2$ and further surpasses the ANN baseline at $T=4$. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.07808 — 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 2026-10-07T11:19:24.919Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).