Login / Signup

Improve Robustness of Reinforcement Learning against Observation Perturbations via l∞ Lipschitz Policy Networks.

Buqing NieJingtian JiYangqing FuYue Gao
Published in: AAAI (2024)
Keyphrases
  • reinforcement learning
  • markov decision process
  • optimal policy
  • machine learning
  • social networks
  • network analysis
  • computer networks
  • function approximation
  • pointwise
  • action selection
  • rl algorithms