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 many robotic applications, some aspects of the system dynamics can bemodeled accurately while others are difficult to obtain or model. We present anovel reinforcement learning (RL) method for continuous state and action spacesthat learns with partial knowledge of the system and without activeexploration. It solves linearly-solvable Markov decision processes (L-MDPs),which are well suited for continuous state and action spaces, based on anactor-critic architecture. Compared to previous RL methods for L-MDPs and pathintegral methods which are model based, the actor-critic learning does not needa model of the uncontrolled dynamics and, importantly, transition noise levels;however, it requires knowing the control dynamics for the problem. We evaluateour method on two synthetic test problems, and one real-world problem insimulation and using real traffic data. Our experiments demonstrate improvedlearning and policy performance.

Actor-Critic for Linearly-Solvable Continuous MDP with Partially Known Dynamics