The paper investigates continuous‑time stochastic control problems with unknown drift and running reward functions, using an exploratory reinforcement learning framework that incorporates relaxed controls and entropy regularization. It develops policy‑iteration algorithms based on probabilistic representations of the optimal value function and its gradient, proving convergence and demonstrating performance through numerical examples. The study also extends to a special case with control‑dependent diffusion, requiring a Hessian representation.
By Jin Ma, Gaozhan Wang, Jianfeng Zhang, Xunyu Zhou
The paper introduces BeTINN, a structured conditional neural network architecture that extends time‑induced modulation with multi‑directional time‑parameter conditioning and a joint residual pathway. BeTINN is evaluated on the Heston stochastic‑volatility PDE, showing improved accuracy for both option values and key sensitivity metrics compared to baseline models. Ablation studies highlight the contributions of each architectural component, and the authors observe that physics‑based validation loss does not fully capture derivative fidelity, underscoring the need for derivative‑aware evaluation when sensitivities are important.
By Jose Miguel Lara Rangel, Mixtli Vazquez Mendoza
arXiv:2406. 14340v2 Announce Type: replace-cross Abstract: The standard stochastic gradient descent (SGD) optimization method, as well as adaptive methods such as the Adam optimizer fail to converge if the learning rates do not converge to zero (particularly, in the situation of constant learning rates).
By Steffen Dereich, Arnulf Jentzen, Adrian Riekert
arXiv:2608. 04778v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) incorporate governing equations into neural-network training and can approximate PDE solutions without requiring large observational datasets.
By Xujia Chen, Xinyue Hu, Letian Chen, Yi Liu, Wenhui Fan
The paper introduces a model‑free continuous‑time reinforcement learning algorithm that learns from a fixed batch of discrete‑time off‑policy data. It builds on the PhiBE‑Q framework to create a PhiBE‑PI policy iteration that uses a single state‑action critic, avoiding explicit drift or diffusion estimation. The authors provide a local end‑to‑end suboptimality guarantee under linear function approximation, analyze error propagation from discretization, function approximation, and finite samples, and reveal a bias‑variance trade‑off where finer time discretization can worsen statistical error.
By Chaorui Yao, Yuming Paul Zhang, Lin Yang, Yuhua Zhu
arXiv:2606. 04275v1 Announce Type: cross Abstract: We present a novel theoretical framework for deep reinforcement learning (RL) in continuous environments by modeling the problem as a continuous-time stochastic process, drawing on insights from stochastic control.
By Saket Tiwari, Tejas Kotwal, George Konidaris