ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2502.07764
75
0

Polynomial-Time Approximability of Constrained Reinforcement Learning

11 February 2025
Jeremy McMahan
ArXivPDFHTML
Abstract

We study the computational complexity of approximating general constrained Markov decision processes. Our primary contribution is the design of a polynomial time (0,ϵ)(0,\epsilon)(0,ϵ)-additive bicriteria approximation algorithm for finding optimal constrained policies across a broad class of recursively computable constraints, including almost-sure, chance, expectation, and their anytime variants. Matching lower bounds imply our approximation guarantees are optimal so long as P≠NPP \neq NPP=NP. The generality of our approach results in answers to several long-standing open complexity questions in the constrained reinforcement learning literature. Specifically, we are the first to prove polynomial-time approximability for the following settings: policies under chance constraints, deterministic policies under multiple expectation constraints, policies under non-homogeneous constraints (i.e., constraints of different types), and policies under constraints for continuous-state processes.

View on arXiv
@article{mcmahan2025_2502.07764,
  title={ Polynomial-Time Approximability of Constrained Reinforcement Learning },
  author={ Jeremy McMahan },
  journal={arXiv preprint arXiv:2502.07764},
  year={ 2025 }
}
Comments on this paper