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/

Zendy Plus

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

Zendy Tools

Zendy Open

Deep reinforcement learning (DRL) has significantly advanced the field ofcombinatorial optimization (CO). However, its practicality is hindered by thenecessity for a large number of reward evaluations, especially in scenariosinvolving computationally intensive function assessments. To enhance the sampleefficiency, we propose a simple but effective method, called symmetric replaytraining (SRT), which can be easily integrated into various DRL methods. Ourmethod leverages high-reward samples to encourage exploration of theunder-explored symmetric regions without additional online interactions - free.Through replay training, the policy is trained to maximize the likelihood ofthe symmetric trajectories of discovered high-rewarded samples. Experimentalresults demonstrate the consistent improvement of our method in sampleefficiency across diverse DRL methods applied to real-world tasks, such asmolecular optimization and hardware design.

Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization