Metraipolis › archive › dc_4aab78281ea8

FB-MOAC: A Reinforcement Learning Algorithm for Forward-Backward Markov Decision Processes — arXiv:2611.00130

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00130
License (as archived)
CC0-1.0
Archived
2026-11-03T10:34:02.468Z
SHA-256 of the archived text
5223ca50cf0add925ba6792f6dd759be955fd2c93574829b8b7b49da789e5cfd
Stable URL of this page
https://metraipolis.com/documento/dc_4aab78281ea8

How to cite

FB-MOAC: A Reinforcement Learning Algorithm for Forward-Backward Markov Decision Processes — arXiv:2611.00130 — arXiv (en), https://arxiv.org/abs/2611.00130 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4aab78281ea8 (Metraipolis archive dc_4aab78281ea8, sha256 5223ca50cf0add925ba6792f6dd759be955fd2c93574829b8b7b49da789e5cfd)
BibTeX
@misc{dc4aab78281ea8,
  title = {FB-MOAC: A Reinforcement Learning Algorithm for Forward-Backward Markov Decision Processes — arXiv:2611.00130},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00130},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4aab78281ea8; sha256 5223ca50cf0add925ba6792f6dd759be955fd2c93574829b8b7b49da789e5cfd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00130. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reinforcement learning (RL) algorithms are effective in solving problems that can be modeled as Markov decision processes (MDPs). These algorithms primarily target forward MDPs whose dynamics evolve over time from an initial state. However, several important problems in different scenarios including stochastic control and network systems exhibit both a forward and a backward dynamics. As a consequence, they cannot be expressed as a standard MDP, thereby calling for a novel theory for RL in this context. Accordingly, this work introduces the concept of Forward-Backward Markov Decision Processes (FB-MDPs) for multi-objective problems, develops a novel theoretical framework to characterize their optimal solutions, and proposes a general forward-backward step-wise template that allows to adapt RL algorithms for FB-MDP problems. A Forward Backward Multi Objective Actor Critic (FB-MOAC) algorithm is introduced accordingly to obtain optimal policies with guaranteed convergence and a competitive rate with respect to standard approaches in RL. FB-MOAC is evaluated on diverse use cases in the context of mathematical finance and mobile resource management. The obtained results show that FB-MOAC outperforms the state of the art across different metrics, highlighting its ability to learn and maximize rewards.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00130 — 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 2026-11-03T10:29:48.672Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).