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

Recently deep reinforcement learning (DRL) has achieved outstanding successon solving many difficult and large-scale RL problems. However the high samplecost required for effective learning often makes DRL unaffordable inresource-limited applications. With the aim of improving sample efficiency andlearning performance, we will develop a new DRL algorithm in this paper thatseamless integrates entropy-induced and bootstrap-induced techniques forefficient and deep exploration of the learning environment. Specifically, ageneral form of Tsallis entropy regularizer will be utilized to driveentropy-induced exploration based on efficient approximation of optimalaction-selection policies. Different from many existing works that rely onaction dithering strategies for exploration, our algorithm is efficient inexploring actions with clear exploration value. Meanwhile, by employing anensemble of Q-networks under varied Tsallis entropy regularization, thediversity of the ensemble can be further enhanced to enable effectivebootstrap-induced exploration. Experiments on Atari game playing tasks clearlydemonstrate that our new algorithm can achieve more efficient and effectiveexploration for DRL, in comparison to recently proposed exploration methodsincluding Bootstrapped Deep Q-Network and UCB Q-Ensemble.

Effective Exploration for Deep Reinforcement Learning via Bootstrapped Q-Ensembles under Tsallis Entropy Regularization