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 (IL) is a framework that learns to imitate expert behaviorfrom demonstrations. Recently, IL shows promising results on high dimensionaland control tasks. However, IL typically suffers from sample inefficiency interms of environment interaction, which severely limits their application tosimulated domains. In industrial applications, learner usually have a highinteraction cost, the more interactions with environment, the more damage itcauses to the environment and the learner itself. In this article, we make aneffort to improve sample efficiency by introducing a novel scheme of inversereinforcement learning. Our method, which we call \textit{Model Reward FunctionBased Imitation Learning} (MRFIL), uses an ensemble dynamic model as a rewardfunction, what is trained with expert demonstrations. The key idea is toprovide the agent with an incentive to match the demonstrations over a longhorizon, by providing a positive reward upon encountering states in line withthe expert demonstration distribution. In addition, we demonstrate theconvergence guarantee for new objective function. Experimental results showthat our algorithm reaches the competitive performance and significantlyreducing the environment interactions compared to IL methods.

Sample Efficient Imitation Learning via Reward Function Trained in Advance