research
∙
05/25/2023
Characterizing Out-of-Distribution Error via Optimal Transport
Out-of-distribution (OOD) data poses serious challenges in deployed mach...
share
research
∙
02/04/2022
SMODICE: Versatile Offline Imitation Learning via State Occupancy Matching
We propose State Matching Offline DIstribution Correction Estimation (SM...
research
∙
12/14/2021
Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning
Reinforcement Learning (RL) agents in the real world must satisfy safety...
research
∙
04/27/2019