The paper investigates combining Reinforcement Learning (RL) with search-based path planners to accelerate flight trajectory optimization for airliners. An RL agent is trained to generate near‑optimal paths from location and atmospheric data, which then constrain a traditional solver to reduce its search space. Experiments using Airbus performance models show that fuel consumption deviates by less than 1% from an unconstrained solver while computation time improves by up to 50%.
By Alberto Luise, Michele Lombardi
The paper introduces a framework for optimal policy improvement in reinforcement learning, defining it as the best single update under given constraints. It shows that restricting improvement to a subset of states is equivalent to solving an induced Markov Decision Process, linking planning with explicit or implicit models to optimal policy improvement. The authors develop a novel operator for greedification under approximate evaluation, demonstrating empirical gains across several RL algorithms and settings.
By Yaniv Oren, Viliam Vadocz, Wiktor Zabka, Thomas Evers, Jan Robine, Wendelin B\"ohmer, Matthijs T. J. Spaan, Martha White, Hendrik Baier, Fenghui Yu
This paper presents a distribution-agnostic robust trajectory-optimization framework based on chance-constrained reinforcement learning. The uncertainty is represented here through initial conditions and process noise, with the only requirement being that it can be sampled.
The paper proposes an online learning framework for configuring dynamic constellation topologies in satellite networks, addressing the challenges posed by continuous orbital movement and node maneuvering. It does not rely on predefined orbital plane structures, making it robust to changes caused by satellite maneuvers. Experiments show that the method performs comparably to state‑of‑the‑art offline techniques and can be adapted to constrained online learning, balancing per‑iteration computational cost against convergence speed.
By Jo\~ao Norberto, Ricardo Ferreira, Cl\'audia Soares
arXiv:2606. 31291v1 Announce Type: new Abstract: Deep reinforcement learning has the potential to solve attitude control problems more adaptively, precisely, and robustly by handling nonlinear dynamics, uncertainties, and failure cases more effectively than traditional attitude control approaches.
By Alexander Fabisch, Melvin Laux, Mariela De Lucas \'Alvarez, Edoardo Caroselli, Julian Theis
The paper introduces a reinforcement‑learning‑guided evolutionary policy optimization framework for scheduling heterogeneous agile Earth observation satellites, addressing task selection, satellite assignment, and sequencing under diverse visibility windows, maneuvering constraints, energy use, and storage limits. It combines assignment‑based indirect encoding with decoder‑based cost evaluation to capture satellite‑dependent constraints while integrating task gain, energy savings, and load balance into a single utility metric. The resulting RLOSMEA algorithm uses reinforcement learning to select high‑level search operators, achieving higher weighted utility and more stable convergence than baseline metaheuristics across varied AEOS scenarios.
By He Wang, Junyu Wu, Hui Li, Yanjie Song, Witold Pedrycz, Liang Li
The paper introduces IQACO, an implicit Q‑learning‑bootstrapped ant colony optimization algorithm for scheduling maritime moving‑target observations with agile Earth‑observation satellites. IQACO embeds an offline implicit Q‑learning module into the ant colony framework to adaptively adjust pheromone, heuristic, and evaporation parameters based on a compact search‑state representation. Experiments on 14 scenarios show IQACO outperforms conventional ant colony optimization, improving mean observation benefit by 3.40%–9.40%, accelerating convergence, and maintaining stability across different objective‑weight settings.
By He Wang, Junyu Wu, Yeye Liu, Yifan Zhou, Jie Zhang, Hui Li, Yanjie Song, Liang Li
arXiv:2606. 25593v1 Announce Type: new Abstract: We study optimal-policy geometry in structured Markov decision processes.
By Fredy Pokou (CRIStAL)
We study optimal-policy geometry in structured Markov decision processes. While approximate dynamic programming and reinforcement learning typically approximate high-dimensional value functions, we show that optimal policies induce simpler decision tessellations.
arXiv:2610.41647v1 Announce Type: new
Abstract: Multi-target on-orbit servicing missions require planning tools that can adapt to evolving operational conditions while accounting for the outcome vari...
By Adam Abdin (LGI)
arXiv:2608. 09628v1 Announce Type: new Abstract: Collision avoidance systems are commonly used to avoid fragmentation events occurring in Low-Earth Orbit (LEO) and Geosynchronous Equatorial Orbit (GEO).
By Logan Luna (Georgia Institute of Technology), Juan Ortiz Couder (Embry-Riddle Aeronautical University), Raul Alejandro Vargas-Acosta (Embry-Riddle Aeronautical University)
arXiv:2510. 03494v2 Announce Type: replace Abstract: We study finite-horizon offline reinforcement learning (RL) with function approximation for both policy evaluation and policy optimization.
By Volodymyr Tkachuk, Csaba Szepesv\'ari, Xiaoqi Tan