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

When we design and deploy an Reinforcement Learning (RL) agent, rewardfunctions motivates agents to achieve an objective. An incorrect or incompletespecification of the objective can result in behavior that does not align withhuman values - failing to adhere with social and moral norms that are ambiguousand context dependent, and cause undesired outcomes such as negative sideeffects and exploration that is unsafe. Previous work have manually definedreward functions to avoid negative side effects, use human oversight for safeexploration, or use foundation models as planning tools. This work studies theability of leveraging Large Language Models (LLM)' understanding of moralityand social norms on safe exploration augmented RL methods. This work evaluateslanguage model's result against human feedbacks and demonstrates languagemodel's capability as direct reward signals.

Towards Socially and Morally Aware RL agent: Reward Design With LLM