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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The exploration-exploitation trade-off is at the heart of reinforcementlearning (RL). However, most continuous control benchmarks used in recent RLresearch only require local exploration. This led to the development ofalgorithms that have basic exploration capabilities, and behave poorly inbenchmarks that require more versatile exploration. For instance, asdemonstrated in our empirical study, state-of-the-art RL algorithms such asDDPG and TD3 are unable to steer a point mass in even small 2D mazes. In thispaper, we propose a new algorithm called "Plan, Backplay, Chain Skills" (PBCS)that combines motion planning and reinforcement learning to solve hardexploration environments. In a first phase, a motion planning algorithm is usedto find a single good trajectory, then an RL algorithm is trained using acurriculum derived from the trajectory, by combining a variant of the Backplayalgorithm and skill chaining. We show that this method outperformsstate-of-the-art RL algorithms in 2D maze environments of various sizes, and isable to improve on the trajectory obtained by the motion planning phase.

PBCS : Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning