Fighting Copycat Agents in Behavioral Cloning from Observation Histories

Chuan Wen
Chuan Wen
Jierui Lin
Jierui Lin
Dinesh Jayaraman
Dinesh Jayaraman
Yang Gao
Yang Gao

NeurIPS, 2020.

Cited by: 0|Bibtex|Views16
EI
Other Links: arxiv.org|dblp.uni-trier.de|academic.microsoft.com

Abstract:

Imitation learning trains policies to map from input observations to the actions that an expert would choose. In this setting, distribution shift frequently exacerbates the effect of misattributing expert actions to nuisance correlates among the observed variables. We observe that a common instance of this causal confusion occurs in par...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments