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

We introduce a curriculum learning algorithm, Variational AutomaticCurriculum Learning (VACL), for solving challenging goal-conditionedcooperative multi-agent reinforcement learning problems. We motivate ourparadigm through a variational perspective, where the learning objective can bedecomposed into two terms: task learning on the current task distribution, andcurriculum update to a new task distribution. Local optimization over thesecond term suggests that the curriculum should gradually expand the trainingtasks from easy to hard. Our VACL algorithm implements this variationalparadigm with two practical components, task expansion and entity progression,which produces training curricula over both the task configurations as well asthe number of entities in the task. Experiment results show that VACL solves acollection of sparse-reward problems with a large number of agents.Particularly, using a single desktop machine, VACL achieves 98% coverage ratewith 100 agents in the simple-spread benchmark and reproduces the ramp-usebehavior originally shown in OpenAI's hide-and-seek project. Our projectwebsite is at https://sites.google.com/view/vacl-neurips-2021.

Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems