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

This paper proposes a new reinforcement learning (RL) algorithm that enhancesexploration by amplifying the imitation effect (AIE). This algorithm consistsof self-imitation learning and random network distillation algorithms. We arguethat these two algorithms complement each other and that combining these twoalgorithms can amplify the imitation effect for exploration. In addition, byadding an intrinsic penalty reward to the state that the RL agent frequentlyvisits and using replay memory for learning the feature state when using anexploration bonus, the proposed approach leads to deep exploration and deviatesfrom the current converged policy. We verified the exploration performance ofthe algorithm through experiments in a two-dimensional grid environment. Inaddition, we applied the algorithm to a simulated environment of unmannedcombat aerial vehicle (UCAV) mission execution, and the empirical results showthat AIE is very effective for finding the UCAV's shortest flight path to avoidan enemy's missiles.

Amplifying the Imitation Effect for Reinforcement Learning of UCAV's Mission Execution