arXiv:2603.27803v1 Announce Type: new
Abstract: We provide a distributed online algorithm for multi-agent submodular maximization under communication delays. We are motivated by the future distributed information-gathering tasks in unknown and dynamic…
arXiv:2509.24305v2 Announce Type: replace
Abstract: We study distributed reinforcement learning (RL) with policy gradient methods under asynchronous and parallel computations and communications. While non-distributed methods are well understood theore…
arXiv:2603.27874v1 Announce Type: new
Abstract: Relative temporal-difference (TD) learning was introduced to mitigate the slow convergence of TD methods when the discount factor approaches one by subtracting a baseline from the temporal-difference upd…
arXiv:2603.27884v1 Announce Type: new
Abstract: We study safe reinforcement learning in finite-horizon linear mixture constrained Markov decision processes (CMDPs) with adversarial rewards under full-information feedback and an unknown transition kern…
arXiv:2512.17374v3 Announce Type: replace
Abstract: Given a probability distribution $\mu$ in $\mathbb{R}^d$ represented by data, we study in this paper the generative modeling of the corresponding conditional probability distributions on the level-se…
arXiv:2603.26542v1 Announce Type: cross
Abstract: Buffer zones are essential in production systems to decouple sequential processes. In dense floor storage environments, such as space-constrained brownfield facilities, manual operation is increasingly…
arXiv:2312.10666v2 Announce Type: replace
Abstract: Trajectory Optimization (TO) and Reinforcement Learning (RL) are powerful and complementary tools to solve optimal control problems. On the one hand, TO can efficiently compute locally-optimal soluti…
arXiv:2510.05516v2 Announce Type: replace
Abstract: Bayesian optimization (BO) is effective for expensive black-box problems but remains challenging in high dimensions. We propose NeST-BO, a curvature-aware local BO method that targets a (modified) Ne…
arXiv:2603.25954v1 Announce Type: new
Abstract: The use of satellite networks has increased significantly in recent years due to their advantages over purely terrestrial systems, such as higher availability and coverage. However, to effectively provid…
arXiv:2603.26231v1 Announce Type: new
Abstract: Synchronous federated learning scales poorly due to the straggler effect. Asynchronous algorithms increase the update throughput by processing updates upon arrival, but they introduce two fundamental cha…