Metraipolis › archive › dc_44fec62f71b4

Provably Efficient Reinforcement Learning in Continuous-Time Episodic MDPs with Poisson Decision Epochs — arXiv:2609.23127

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23127
License (as archived)
CC0-1.0
Archived
2026-10-09T07:07:03.417Z
SHA-256 of the archived text
ac7e16adc31c183c0d94be73f2c13ec2d7543685b8da264ea5de604cf1b2f15a
Stable URL of this page
https://metraipolis.com/documento/dc_44fec62f71b4

How to cite

Provably Efficient Reinforcement Learning in Continuous-Time Episodic MDPs with Poisson Decision Epochs — arXiv:2609.23127 — arXiv (en), https://arxiv.org/abs/2609.23127 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44fec62f71b4 (Metraipolis archive dc_44fec62f71b4, sha256 ac7e16adc31c183c0d94be73f2c13ec2d7543685b8da264ea5de604cf1b2f15a)
BibTeX
@misc{dc44fec62f71b4,
  title = {Provably Efficient Reinforcement Learning in Continuous-Time Episodic MDPs with Poisson Decision Epochs — arXiv:2609.23127},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23127},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44fec62f71b4; sha256 ac7e16adc31c183c0d94be73f2c13ec2d7543685b8da264ea5de604cf1b2f15a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23127. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Many real-world reinforcement learning (RL) problems evolve in continuous time, where decisions occur at irregular, event-driven intervals rather than at fixed discrete steps. We study episodic continuous-time Markov Decision Processes (MDPs) in which decision epochs are governed by a homogeneous Poisson process and the reward and transition dynamics vary smoothly over time. We consider both a fixed number of jumps per episode and a fixed time budget with a random number of Poisson decision epochs. Under a Lipschitz continuity assumption in time, we exploit local smoothness through discretization and extend both UCRL (Auer and Ortner 2006) and Q-learning (Jin et al. 2018) to this setting, proving $\widetilde{O}(T^{2/3})$ regret bounds for both model-based and model-free algorithms. Finally, we establish matching $\widetilde{\Omega}(T^{2/3})$ minimax lower bounds, showing that the rate is optimal up to logarithmic factors. These results provide the first tight regret guarantees for Lipschitz-smooth continuous-time episodic MDPs with Poisson decision epochs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.23127 — 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 2026-10-09T06:58:09.269Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).