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 examine the question of when and how parametric models are most useful inreinforcement learning. In particular, we look at commonalities and differencesbetween parametric models and experience replay. Replay-based learningalgorithms share important traits with model-based approaches, including theability to plan: to use more computation without additional data to improvepredictions and behaviour. We discuss when to expect benefits from eitherapproach, and interpret prior work in this context. We hypothesise that, undersuitable conditions, replay-based algorithms should be competitive to or betterthan model-based algorithms if the model is used only to generate fictionaltransitions from observed states for an update rule that is otherwisemodel-free. We validated this hypothesis on Atari 2600 video games. Thereplay-based algorithm attained state-of-the-art data efficiency, improvingover prior results with parametric models.

When to use parametric models in reinforcement learning?