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

Inferring reward functions from demonstrations and pairwise preferences areauspicious approaches for aligning Reinforcement Learning (RL) agents withhuman intentions. However, state-of-the art methods typically focus on learninga single reward model, thus rendering it difficult to trade off differentreward functions from multiple experts. We propose Multi-Objective ReinforcedActive Learning (MORAL), a novel method for combining diverse demonstrations ofsocial norms into a Pareto-optimal policy. Through maintaining a distributionover scalarization weights, our approach is able to interactively tune a deepRL agent towards a variety of preferences, while eliminating the need forcomputing multiple policies. We empirically demonstrate the effectiveness ofMORAL in two scenarios, which model a delivery and an emergency task thatrequire an agent to act in the presence of normative conflicts. Overall, weconsider our research a step towards multi-objective RL with learned rewards,bridging the gap between current reward learning and machine ethics literature.

MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning