Temporal Regularization for Markov Decision Process
Pierre Thodoroff, Audrey Durand, Joelle Pineau, Doina Precup
–Neural Information Processing Systems
Yetinreinforcementlearning,duetothenatureofthe Bellman equation, there isanopportunity toalsoexploit temporal regularization based on smoothness in value estimates over trajectories. This paper explores a class of methods for temporal regularization.
Neural Information Processing Systems
Feb-12-2026, 18:55:45 GMT