English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Behavioral cloning has proven to be effective for learning sequentialdecision-making policies from expert demonstrations. However, behavioralcloning often suffers from the causal confusion problem where a policy relieson the noticeable effect of expert actions due to the strong correlation butnot the cause we desire. This paper presents Object-aware REgularizatiOn(OREO), a simple technique that regularizes an imitation policy in anobject-aware manner. Our main idea is to encourage a policy to uniformly attendto all semantic objects, in order to prevent the policy from exploitingnuisance variables strongly correlated with expert actions. To this end, weintroduce a two-stage approach: (a) we extract semantic objects from images byutilizing discrete codes from a vector-quantized variational autoencoder, and(b) we randomly drop the units that share the same discrete code together,i.e., masking out semantic objects. Our experiments demonstrate that OREOsignificantly improves the performance of behavioral cloning, outperformingvarious other regularization and causality-based methods on a variety of Atarienvironments and a self-driving CARLA environment. We also show that our methodeven outperforms inverse reinforcement learning methods trained with aconsiderable amount of environment interaction.

Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning