Metraipolis › archive › dc_832fd7a8faaf

Reinforcement Learning with Complex (valued) Memories — arXiv:2609.38598

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38598
License (as archived)
CC0-1.0
Archived
2026-10-07T13:45:24.005Z
SHA-256 of the archived text
a2202331700795d529f41e8dc4dda81e23f1b588c60f0d836d3fa6a3787e9862
Stable URL of this page
https://metraipolis.com/documento/dc_832fd7a8faaf

How to cite

Reinforcement Learning with Complex (valued) Memories — arXiv:2609.38598 — arXiv (en), https://arxiv.org/abs/2609.38598 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_832fd7a8faaf (Metraipolis archive dc_832fd7a8faaf, sha256 a2202331700795d529f41e8dc4dda81e23f1b588c60f0d836d3fa6a3787e9862)
BibTeX
@misc{dc832fd7a8faaf,
  title = {Reinforcement Learning with Complex (valued) Memories — arXiv:2609.38598},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38598},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_832fd7a8faaf; sha256 a2202331700795d529f41e8dc4dda81e23f1b588c60f0d836d3fa6a3787e9862},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38598. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Partially observable environments pose a fundamental challenge in deep reinforcement learning, requiring agents to compress temporal information from observations and maintain a memory to make effective decisions. While there exist many approaches ranging from gated recurrence to attention mechanisms and model-based RL, the search for effective representational techniques that can capture long-term dependencies remains an active area of research. In this work we revisit Unitary recurrent networks (uRNNs) [Arjovsky et al., 2016, Jing et al., 2017], that demonstrated superior gradient flow and associative recall, expressing the recurrence and the hidden state in a complex vector space. Their norm preserving unitary dynamics enable information propagation through long sequences. To this end, we propose three different versions of uRNNs as drop-in replacements for recurrent PPO architectures, and demonstrate that the simple recurrence and the added degree of freedom from the phase of the complex representations enable significant gains over baselines on several memory-improvable tasks, including continuous control. We further explore how to preserve the phase information of the complex hidden state for a phase-aware policy by drawing a parallel to how quantum states are measured. With our methods reaching up to 2-3 $\times$ the reward in environments like rocksample and Craftax compared to the baselines, this work points towards an exciting new direction of representations for RL and the problem of partial observability. Code is available at: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.38598 — 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 2026-10-07T13:18:10.228Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).