arXiv:2608. 19587v1 Announce Type: new Abstract: While entropy regularization is widely used to stabilize and accelerate Natural Policy Gradient methods, its ability to yield faster convergence rates for the unregularized objective remains underexplored.
By Zhiqiang Tan
arXiv:2606. 18186v1 Announce Type: cross Abstract: Finite-dimensional (FD) diffusion policies exhibit temporal drift owing to discretization artifacts that degrade long-horizon performance (when deployed on physical systems).
By Lekan Molu
While entropy regularization is widely used to stabilize and accelerate Natural Policy Gradient methods, its ability to yield faster convergence rates for the unregularized objective remains underexplored. Existing analyses often rely on double-loop architectures and invoke a linear entropy penalty.
The paper presents a theoretical study of Adam in non‑stationary stochastic optimization, distinguishing two regimes: Euclidean tracking under adaptive strong monotonicity and high‑probability projected stationarity for general smooth objectives. It derives finite‑time bounds that decompose into initialization, objective drift, first‑moment tracking error (β₁), and preconditioner perturbation (β₂), and characterizes burn‑in times for constant and step‑decay schedules. The analysis reveals a noise–drift tradeoff, showing that in noise‑dominated settings Adam’s adaptive mechanisms can improve guarantees, while in drift‑dominated settings they may worsen tracking, potentially making vanilla SGD preferable.
By Sharan Sahu, Abir Sarkar, Cameron J. Hogan, Martin T. Wells
arXiv:2610. 13901v1 Announce Type: cross Abstract: We study the last iterate of standard asynchronous Q-learning from a single trajectory of a finite Markov decision process.
By Yang Peng
arXiv:2609. 38880v2 Announce Type: replace-cross Abstract: We study the last iterate of standard importance-weighted temporal-difference (TD) learning from a single trajectory of a finite Markov decision process.
By Yang Peng