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

Model-based Reinforcement Learning (RL) is a popular learning paradigm due toits potential sample efficiency compared to model-free RL. However, existingempirical model-based RL approaches lack the ability to explore. This workstudies a computationally and statistically efficient model-based algorithm forboth Kernelized Nonlinear Regulators (KNR) and linear Markov Decision Processes(MDPs). For both models, our algorithm guarantees polynomial sample complexityand only uses access to a planning oracle. Experimentally, we first demonstratethe flexibility and efficacy of our algorithm on a set of explorationchallenging control tasks where existing empirical model-based RL approachescompletely fail. We then show that our approach retains excellent performanceeven in common dense reward control benchmarks that do not require heavyexploration. Finally, we demonstrate that our method can also performreward-free exploration efficiently. Our code can be found athttps://github.com/yudasong/PCMLP.

PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration