research
∙
06/02/2023
PAGAR: Imitation Learning with Protagonist Antagonist Guided Adversarial Reward
Imitation learning (IL) algorithms often rely on inverse reinforcement l...
share
research
∙
03/31/2023
POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems
Neural networks (NNs) playing the role of controllers have demonstrated ...
research
∙
04/20/2022
A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines
A misspecified reward can degrade sample efficiency and induce undesired...
research
∙
12/14/2021
Programmatic Reward Design by Example
Reward design is a fundamental problem in reinforcement learning (RL). A...
research
∙
08/17/2020
Runtime-Safety-Guided Policy Repair
We study the problem of policy repair for learning-based control policie...
research
∙
10/22/2017