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

Imitation learning, followed by reinforcement learning algorithms, is apromising paradigm to solve complex control tasks sample-efficiently. However,learning from demonstrations often suffers from the covariate shift problem,which results in cascading errors of the learned policy. We introduce a notionof conservatively-extrapolated value functions, which provably lead to policieswith self-correction. We design an algorithm Value Iteration with NegativeSampling (VINS) that practically learns such value functions with conservativeextrapolation. We show that VINS can correct mistakes of the behavioral cloningpolicy on simulated robotics benchmark tasks. We also propose the algorithm ofusing VINS to initialize a reinforcement learning algorithm, which is shown tooutperform significantly prior works in sample efficiency.

Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling