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

Classical reinforcement learning (RL) has generated excellent results indifferent regions; however, its sample inefficiency remains a critical issue.In this paper, we provide concrete numerical evidence that the sampleefficiency (the speed of convergence) of quantum RL could be better than thatof classical RL, and for achieving comparable learning performance, quantum RLcould use much (at least one order of magnitude) fewer trainable parametersthan classical RL. Specifically, we employ the popular benchmarkingenvironments of RL in the OpenAI Gym, and show that our quantum RL agentconverges faster than classical fully-connected neural networks (FCNs) in thetasks of CartPole and Acrobot under the same optimization process. We alsosuccessfully train the first quantum RL agent that can complete the task ofLunarLander in the OpenAI Gym. Our quantum RL agent only requires asingle-qubit-based variational quantum circuit without entangling gates,followed by a classical neural network (NN) to post-process the measurementoutput. Finally, we could accomplish the aforementioned tasks on the real IBMquantum machines. To the best of our knowledge, none of the earlier quantum RLagents could do that.

Unentangled quantum reinforcement learning agents in the OpenAI Gym