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

Multi-Task Reinforcement Learning (MTRL) tackles the long-standing problem ofendowing agents with skills that generalize across a variety of problems. Tothis end, sharing representations plays a fundamental role in capturing bothunique and common characteristics of the tasks. Tasks may exhibit similaritiesin terms of skills, objects, or physical properties while leveraging theirrepresentations eases the achievement of a universal policy. Nevertheless, thepursuit of learning a shared set of diverse representations is still an openchallenge. In this paper, we introduce a novel approach for representationlearning in MTRL that encapsulates common structures among the tasks usingorthogonal representations to promote diversity. Our method, named Mixture OfOrthogonal Experts (MOORE), leverages a Gram-Schmidt process to shape a sharedsubspace of representations generated by a mixture of experts. Whentask-specific information is provided, MOORE generates relevant representationsfrom this shared subspace. We assess the effectiveness of our approach on twoMTRL benchmarks, namely MiniGrid and MetaWorld, showing that MOORE surpassesrelated baselines and establishes a new state-of-the-art result on MetaWorld.

Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts