Reinforcement Learning for Stochastic Networks, Toulouse

Session

Keynote: Emmanuel Rachelson (ISAE-SUPAERO)

Jun 21, 2024, 9:30 AM

Amphi B00 (ENSEEIHT)

89. Lipschitz Lifelong Reinforcement Learning: transferring value functions across MDPs

6/21/24, 9:30 AM

Abstract: How close are the optimal value functions of two Markov decision processes that share the same state and action spaces but have different dynamics and rewards? In this talk, we will consider the problem of knowledge transfer when an agent is facing a series of reinforcement learning (RL) tasks. We will introduce a novel metric between Markov decision processes (MDPs) and establish...