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 exploration mechanism used by a Deep Reinforcement Learning (RL) agentplays a key role in determining its sample efficiency. Thus, improving overrandom exploration is crucial to solve long-horizon tasks with sparse rewards.We propose to leverage an ensemble of partial solutions as teachers that guidethe agent's exploration with action suggestions throughout training. While thesetup of learning with teachers has been previously studied, our proposedapproach - Actor-Critic with Teacher Ensembles (AC-Teach) - is the first towork with an ensemble of suboptimal teachers that may solve only part of theproblem or contradict other each other, forming a unified algorithmic solutionthat is compatible with a broad range of teacher ensembles. AC-Teach leveragesa probabilistic representation of the expected outcome of the teachers' andstudent's actions to direct exploration, reduce dithering, and adapt to thedynamically changing quality of the learner. We evaluate a variant of AC-Teachthat guides the learning of a Bayesian DDPG agent on three tasks - pathfollowing, robotic pick and place, and robotic cube sweeping using a hook - andshow that it improves largely on sampling efficiency over a set of baselines,both for our target scenario of unconstrained suboptimal teachers and foreasier setups with optimal or single teachers. Additional results and videos athttps://sites.google.com/view/acteach/home.

AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers