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

In this paper, two novel practical methods of Reinforcement Learning fromDemonstration (RLfD) are developed and applied to automatic berthing controlsystems for Unmanned Surface Vessel. A new expert data generation method,called Model Predictive Based Expert (MPBE) which combines Model PredictiveControl and Deep Deterministic Policy Gradient, is developed to provide highquality supervision data for RLfD algorithms. A straightforward RLfD method,model predictive Deep Deterministic Policy Gradient (MP-DDPG), is firstlyintroduced by replacing the RL agent with MPBE to directly interact with theenvironment. Then distribution mismatch problem is analyzed for MP-DDPG, andtwo techniques that alleviate distribution mismatch are proposed. Furthermore,another novel RLfD algorithm based on the MP-DDPG, called Self-GuidedActor-Critic (SGAC) is present, which can effectively leverage MPBE bycontinuously querying it to generate high quality expert data online. Thedistribution mismatch problem leading to unstable learning process is addressedby SGAC in a DAgger manner. In addition, theoretical analysis is given to provethat SGAC algorithm can converge with guaranteed monotonic improvement.Simulation results verify the effectiveness of MP-DDPG and SGAC to accomplishthe ship berthing control task, and show advantages of SGAC comparing withother typical reinforcement learning algorithms and MP-DDPG.

Reinforcement Learning from Demonstrations by Novel Interactive Expert  and Application to Automatic Berthing Control Systems for Unmanned Surface  Vessel