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

Many imitation learning (IL) algorithms employ inverse reinforcement learning(IRL) to infer the underlying reward function that an expert is implicitlyoptimizing for, based on their demonstrated behaviors. However, a misalignmentbetween the inferred reward and the true task objective can result in taskfailures. In this paper, we introduce Protagonist Antagonist Guided AdversarialReward (PAGAR), a semi-supervised reward design paradigm to tackle this rewardmisalignment problem in IRL-based IL. We identify the conditions on thecandidate reward functions under which PAGAR can guarantee to induce a policythat succeeds in the underlying task. Furthermore, we present a practicalon-and-off policy approach to implement PAGAR in IRL-based IL. Experimentalresults show that our algorithm outperforms competitive baselines on complex ILtasks and zero-shot IL tasks in transfer environments with limiteddemonstrations.

PAGAR: Taming Reward Misalignment in Inverse Reinforcement Learning-Based Imitation Learning with Protagonist Antagonist Guided Adversarial Reward