What question did this study set out to answer?

This research aims to enhance the differential evolution algorithm using reinforcement learning for better optimization performance.

May 15, 2026PLoS ONEOpen Access

Reinforcement learning-controlled differential evolution with L-BFGS refinements

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates a new algorithm, aiming to improve optimization in discrete combinatorial scenarios.

This research aims to enhance the differential evolution algorithm using reinforcement learning for better optimization performance.
Proposed RL-DE algorithm integrates reinforcement learning for parameter policy refinement.
Evaluated on CEC2017 benchmark test set to assess performance in high-dimensional scenarios.
Application in flexible job shop scheduling problems to verify generalization capability.
RL-DE demonstrates improved performance over classical adaptive DE variants in high-dimensional scenarios.
Achieved effective parameter adaptation resulting in efficient solutions for expensive black box optimization.
Validated ability to solve complex discrete combinatorial optimization problems, such as job shop scheduling.

Cao et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

May 15, 2026PLoS ONEOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates a new algorithm, aiming to improve optimization in discrete combinatorial scenarios.

This research aims to enhance the differential evolution algorithm using reinforcement learning for better optimization performance.
Proposed RL-DE algorithm integrates reinforcement learning for parameter policy refinement.
Evaluated on CEC2017 benchmark test set to assess performance in high-dimensional scenarios.
Application in flexible job shop scheduling problems to verify generalization capability.
RL-DE demonstrates improved performance over classical adaptive DE variants in high-dimensional scenarios.
Achieved effective parameter adaptation resulting in efficient solutions for expensive black box optimization.
Validated ability to solve complex discrete combinatorial optimization problems, such as job shop scheduling.

Cao et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark