← Search

Erwan Lecarpentier

2 accepted papers

2021

Lipschitz Lifelong Reinforcement Learning

AAAI 2021technical

We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks. We introduce a novel metric between Markov Decision Processes and establish that close MDPs have close optimal value functions. Formally, the optimal value functions are Lipschitz con…

2019

Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning

NeurIPS 2019poster

This work tackles the problem of robust zero-shot planning in non-stationary stochastic environments. We study Markov Decision Processes (MDPs) evolving over time and consider Model-Based Reinforcement Learning algorithms in this setting. We make two hypotheses: 1) the environment evolves continuous…