Finite-Sample Analysis for SARSA with Linear Function Approximation

Shaofeng Zou, Tengyu Xu, Yingbin Liang

Oct-3-2025, 08:27:49 GMT–Neural Information Processing Systems

SARSA is an on-policy algorithm to learn a Markov decision process policy in reinforcement learning. We investigate the SARSA algorithm with linear function approximation under the non-i.i.d.

artificial intelligence, machine learning, reinforcement learning, (16 more...)

Neural Information Processing Systems

Oct-3-2025, 08:27:49 GMT

Conferences PDF

Country:
- Europe > United Kingdom
  - England > Cambridgeshire > Cambridge (0.04)
- North America
  - Canada (0.04)
  - United States
    - New York > Erie County
      - Buffalo (0.04)
    - Ohio > Franklin County
      - Columbus (0.04)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Learning Graphical Models > Undirected Networks
      - Markov Models (0.52)
    - Reinforcement Learning (1.00)
  - Representation & Reasoning > Uncertainty
    - Fuzzy Logic (0.63)

Duplicate Docs Excel Report

Title
Finite-Sample Analysis for SARSA with Linear Function Approximation

Similar Docs Excel Report more

Title	Similarity	Source
None found