Wael Fatnassi

Provably Safe Model-Based Meta Reinforcement Learning: An Abstraction-Based Approach

2021 · 2021 60th IEEE Conference on Decision and Control (CDC)

While conventional reinforcement learning focuses on designing agents that can perform one task, meta-learning aims, instead, to solve the problem of designing agents that can generalize to different tasks (e.g., environments, obstacles, and goals) that …