AAMAS 2024
Presented By: Himanshu Gupta
Date: 6/10/2024
Authors: Sangwon Seo, Vaibhav Unhelkar
Traditional IL
IDIL
\( \pi_E = \pi(a|s) \)
X - set of latent states
\( \mathcal{N} = (\pi, \zeta) \)
\( \mathcal{N} = (\pi, \zeta) \)
\( \mathcal{N} = (\pi, \zeta) \)
Q: How do I get \(x\) and \(x^-\) though?
Q: How do I leverage the inherent factorization to get \(\pi\) and \(\zeta\)?
First Theoretical Contribution
\( \mathcal{N} = (\pi, \zeta) \)
Second Theoretical Contribution
IDIL
Objective
IDIL
Objective
\( \mathcal{N} = (\pi, \zeta) \)
Using Viterbi
Algorithm
MultiGoal-n
(continuous)
Movers
(discrete)
Key Takeaway : IDIL does better than other IL methods for problems where diverse human intents exist and can vary over time.
Key Takeaway : IDIL does just as good (or better) as other IL methods for problems where diverse human intents don't exist.
Key Takeaway : IDIL is better at identifying the hidden intent than other IL methods that also consider intent.