Papers › Sample and Computationally Efficient Continuous-Time Reinforcement Learning with...

Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation

20 May 2025arXiv:2505.14821archive 2025-07-28

Runze Zhao, Yue Yu, Adams Yiyue Zhu, Chen Yang, Dongruo Zhou

Continuous-time reinforcement learning (CTRL) provides a principled framework for sequential decision-making in environments where interactions evolve continuously over time. Despite its empirical success, the theoretical understanding of CTRL remains limited, especially in settings with general function approximation. In this work, we propose a model-based CTRL algorithm that achieves both sample and computational efficiency. Our approach leverages optimism-based confidence sets to establish the first sample complexity guarantee for CTRL with general function approximation, showing that a near-optimal policy can be learned with a suboptimality gap of Õ(√(d_ℛ + d_ℱ)N^(-1/2)) using N measurements, where d_ℛ and d_ℱ denote the distributional Eluder dimensions of the reward and dynamic functions, respectively, capturing the complexity of general function approximation in reinforcement learning. Moreover, we introduce structured policy updates and an alternative measurement strategy that significantly reduce the number of policy updates and rollouts while maintaining competitive sample efficiency. We implemented experiments to backup our proposed algorithms on continuous control tasks and diffusion model fine-tuning, demonstrating comparable performance with significantly fewer policy updates and rollouts.

PaperPDFCode

Code

MLIUB/PURE officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Computational EfficiencyContinuous ControlReinforcement LearningSequential Decision Makingcontinuous-controlreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdaGradAttentionBPECTRLDense ConnectionsDiffusionDropoutGradient ClippingLayer NormalizationLinear LayerLinear WarmupMulti-Head AttentionReLUResidual ConnectionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections