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

The aim of path planning is to reach the goal from starting point bysearching for the route of an agent. In the path planning, the routes may varydepending on the number of variables such that it is important for the agent toreach various goals. Numerous studies, however, have dealt with a single goalthat is predefined by the user. In the present study, I propose a novelreinforcement learning framework for a fully controllable agent in the pathplanning. To do this, I propose a bi-directional memory editing to obtainvarious bi-directional trajectories of the agent, in which the behavior of theagent and sub-goals are trained on the goal-conditioned RL. As for moving theagent in various directions, I utilize the sub-goals dedicated network,separated from a policy network. Lastly, I present the reward shaping toshorten the number of steps for the agent to reach the goal. In theexperimental result, the agent was able to reach the various goals that havenever been visited by the agent in the training. We confirmed that the agentcould perform difficult missions such as a round trip and the agent used theshorter route with the reward shaping.

A Fully Controllable Agent in the Path Planning using Goal-Conditioned Reinforcement Learning