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

The deployment of reinforcement learning (RL) in the real world comes withchallenges in calibrating user trust and expectations. As a step towarddeveloping RL systems that are able to communicate their competencies, wepresent a method of generating human-interpretable abstract behavior modelsthat identify the experiential conditions leading to different task executionstrategies and outcomes. Our approach consists of extracting experientialfeatures from state representations, abstracting strategy descriptors fromtrajectories, and training an interpretable decision tree that identifies theconditions most predictive of different RL behaviors. We demonstrate our methodon trajectory data generated from interactions with the environment and onimagined trajectory data that comes from a trained probabilistic world model ina model-based RL setting.

Explaining Conditions for Reinforcement Learning Behaviors from Real and Imagined Data