Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning

Kumar Krishna Agrawal
Kumar Krishna Agrawal
Debidatta Dwibedi
Debidatta Dwibedi

ICLR, 2019.

Cited by: 61|Views129
EI
Weibo:
In this work we address several important issues associated with the popular generative adversarial imitation learning framework

Abstract:

We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework. The first problem is implicit bias present in the reward functions used in these algorithms. While these biases might work well for some environments, they can also lead to sub-optimal behavior in others. Secondly, even though these...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments