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

We consider the problem of learning from demonstrated trajectories withinverse reinforcement learning (IRL). Motivated by a limitation of theclassical maximum entropy model in capturing the structure of the network ofstates, we propose an IRL model based on a generalized version of the causalentropy maximization problem, which allows us to generate a class of maximumentropy IRL models. Our generalized model has an advantage of being able torecover, in addition to a reward function, another expert's function that would(partially) capture the impact of the connecting structure of the states onexperts' decisions. Empirical evaluation on a real-world dataset and agrid-world dataset shows that our generalized model outperforms the classicalones, in terms of recovering reward functions and demonstrated trajectories.

Generalized Maximum Causal Entropy for Inverse Reinforcement Learning