More Research
Iterative-DualRL:
An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning
Haoran Xu
*
1
,
Shuozhe Li
*
1
,
Harshit Sikchi
1
,
Scott Niekum
2
,
Amy Zhang
1,3
1
UT Austin
2
UMass Amherst
2
Meta AI
* Equal contribution
Paper
Code
Under construction.