• 한국정보전자통신기술학회논문지
• /
• 제5권1호
• /
• pp.33-44
• /
• 2012

이 논문에서는 얼개가 새로운 회귀 신경망을 제안하고, 그 신경망이 어떤 이산 시간 동적 시스템도 동정화 할 수 있음을 보인다. 또한, 제안한 신경망을 써서 유한 상태 자동기계를 부호화, 동정화, 그리고 추출하는 데에 적용하여 그 성능을 살펴본다. 제안한 신경망에 고친 비용함수를 쓰고 혼합 그리디 모의 담금질 방법으로 학습시키면 유한 상태 자동기계를 동정화하는 성능이 일반적으로 다른 기법보다 더 낫다는 것을 모의실험으로 보인다.

• Nuclear Engineering and Technology
• /
• 제54권10호
• /
• pp.3864-3877
• /
• 2022

We propose a new approach called PESA (Prioritized replay Evolutionary and Swarm Algorithms) combining prioritized replay of reinforcement learning with hybrid evolutionary algorithms. PESA hybridizes different evolutionary and swarm algorithms such as particle swarm optimization, evolution strategies, simulated annealing, and differential evolution, with a modular approach to account for other algorithms. PESA hybridizes three algorithms by storing their solutions in a shared replay memory, then applying prioritized replay to redistribute data between the integral algorithms in frequent form based on their fitness and priority values, which significantly enhances sample diversity and algorithm exploration. Additionally, greedy replay is used implicitly to improve PESA exploitation close to the end of evolution. PESA features in balancing exploration and exploitation during search and the parallel computing result in an agnostic excellent performance over a wide range of experiments and problems presented in this work. PESA also shows very good scalability with number of processors in solving an expensive problem of optimizing nuclear fuel in nuclear power plants. PESA's competitive performance and modularity over all experiments allow it to join the family of evolutionary algorithms as a new hybrid algorithm; unleashing the power of parallel computing for expensive optimization.