paper-with-me

Papers

Distributional Offline Continuous-Time Reinforcement Learning with Neural Physics-Informed PDEs (SciPhy RL for DOCTR-L)

2021-04-02 · Igor Halperin

This paper addresses distributional offline continuous-time reinforcement learning (DOCTR-L) with stochastic policies for high-dimensional optimal control. A soft distributional version of the classical Hamilton-Jacobi-Bellman (HJB) equation is given by a semilinear partial differential equation (PDE). This soft HJB equation' can be learned from offline data without assuming that the latter correspond to a previous optimal or near-optimal policy. A data-driven solution of the soft HJB equation uses methods of Neural PDEs and Physics-Informed Neural Networks developed in the field of Scientific Machine Learning (SciML). The suggested approach, dubbed SciPhy RL', thus reduces DOCTR-L to solving neural PDEs from data. Our algorithm called Deep DOCTR-L converts offline high-dimensional data into an optimal policy in one step by reducing it to supervised learning, instead of relying on value iteration or policy iteration methods. The method enables a computable approach to the quality control of obtained policies in terms of both their expected returns and uncertainties about their values.

📄 PDF Abstract BibTeX arXiv:2104.01040

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Path-Coupled Bellman Flows for Distributional Reinforcement Learning

2026-05-07 · Boyang Xu, Qing Zou, Siqin Yang, Hao Yan arxiv

Distributional reinforcement learning (DRL) models the full return distribution, but existing finite-support or quantile-based methods rely on projections, while recent flow-based approaches can suffer from \emph{boundar…

Reinforcement LearningOffline RL

Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning

2023-10-18 · Jianlan Luo, Perry Dong, Jeffrey Wu, Aviral Kumar 외

The offline reinforcement learning (RL) paradigm provides a general recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. While policy constraints, cons…

Offline RLQuantizationreinforcement-learningReinforcement Learning+1

Unleashing Flow Policies with Distributional Critics

2025-09-27 · Deshu Chen, Yuchen Liu, Zhijian Zhou, Chao Qu 외 arxiv

Flow-based policies have recently emerged as a powerful tool in offline and offline-to-online reinforcement learning, capable of modeling the complex, multimodal behaviors found in pre-collected datasets. However, the fu…

Reinforcement Learning

Offline Robotic World Model: Learning Robotic Policies without a Physics Simulator

2025-04-23 · Chenhao Li, Andreas Krause, Marco Hutter

Reinforcement Learning (RL) has demonstrated impressive capabilities in robotic control but remains challenging due to high sample complexity, safety concerns, and the sim-to-real gap. While offline RL eliminates the nee…

Offline RLReinforcement Learning (RL)

Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning

2025-09-08 · Vittorio Giammarino, Ruiqi Ni, Ahmed H. Qureshi arxiv

Offline Goal-Conditioned Reinforcement Learning (GCRL) holds great promise for domains such as autonomous navigation and locomotion, where collecting interactive data is costly and unsafe. However, it remains challenging…

Reinforcement Learning