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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper introduces a new method for inverse reinforcement learning inlarge-scale and high-dimensional state spaces. To avoid solving thecomputationally expensive reinforcement learning problems in reward learning,we propose a function approximation method to ensure that the BellmanOptimality Equation always holds, and then estimate a function to maximize thelikelihood of the observed motion. The time complexity of the proposed methodis linearly proportional to the cardinality of the action set, thus it canhandle large state spaces efficiently. We test the proposed method in asimulated environment, and show that it is more accurate than existing methodsand significantly better in scalability. We also show that the proposed methodcan extend many existing methods to high-dimensional state spaces. We thenapply the method to evaluating the effect of rehabilitative stimulations onpatients with spinal cord injuries based on the observed patient motions.

Inverse Reinforcement Learning in Large State Spaces via Function Approximation