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 contribute to micro-data model-based reinforcement learning (MBRL) byrigorously comparing popular generative models using a fixed (random shooting)control agent. We find that on an environment that requires multimodalposterior predictives, mixture density nets outperform all other models by alarge margin. When multimodality is not required, our surprising finding isthat we do not need probabilistic posterior predictives: deterministic modelsare on par, in fact they consistently (although non-significantly) outperformtheir probabilistic counterparts. We also found that heteroscedasticity attraining time, perhaps acting as a regularizer, improves predictions at longerhorizons. At the methodological side, we design metrics and an experimentalprotocol which can be used to evaluate the various models, predicting theirasymptotic performance when using them on the control problem. Using thisframework, we improve the state-of-the-art sample complexity of MBRL on Acrobotby two to four folds, using an aggressive training schedule which is outside ofthe hyperparameter interval usually considered

Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?