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

Meta reinforcement learning (RL) attempts to discover new RL algorithmsautomatically from environment interaction. In so-called black-box approaches,the policy and the learning algorithm are jointly represented by a singleneural network. These methods are very flexible, but they tend to underperformin terms of generalisation to new, unseen environments. In this paper, weexplore the role of symmetries in meta-generalisation. We show that a recentsuccessful meta RL approach that meta-learns an objective forbackpropagation-based learning exhibits certain symmetries (specifically thereuse of the learning rule, and invariance to input and output permutations)that are not present in typical black-box meta RL systems. We hypothesise thatthese symmetries can play an important role in meta-generalisation. Buildingoff recent work in black-box supervised meta learning, we develop a black-boxmeta RL system that exhibits these same symmetries. We show through carefulexperimentation that incorporating these symmetries can lead to algorithms witha greater ability to generalise to unseen action & observation spaces, tasks,and environments.

Introducing Symmetries to Black Box Meta Reinforcement Learning