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

One of the main goals of reinforcement learning (RL) is to provide a~way forphysical machines to learn optimal behavior instead of being programmed.However, effective control of the machines usually requires fine timediscretization. The most common RL methods apply independent random elements toeach action, which is not suitable in that setting. It is not feasible becauseit causes the controlled system to jerk, and does not ensure sufficientexploration since a~single action is not long enough to create a~significantexperience that could be translated into policy improvement. In our view theseare the main obstacles that prevent application of RL in contemporary controlsystems. To address these pitfalls, in this paper we introduce an RL frameworkand adequate analytical tools for actions that may be stochastically dependentin subsequent time instances. We also introduce an RL algorithm thatapproximately optimizes a~policy that produces such actions. It appliesexperience replay to adjust likelihood of sequences of previous actions tooptimize expected $n$-step returns the policy yields. The efficiency of thisalgorithm is verified against four other RL methods (CDAU, PPO, SAC, ACER) infour simulated learning control problems (Ant, HalfCheetah, Hopper, andWalker2D) in diverse time discretization. The algorithm introduced hereoutperforms the competitors in most cases considered.

ACERAC: Efficient reinforcement learning in fine time discretization