H Bai, R Cheng, Y Jin - Intelligent Computing, 2023 - spj.science.org
… In contrast, a general computational reward framework from the evolutionaryperspective … environment, the multi-agent evolutionaryreinforcementlearning (MERL) method maintains …
S Khadka, K Tumer - arXiv preprint arXiv:1805.07917, 2018 - researchgate.net
… an evolutionaryperspective, combining RL with EA is closely related to the idea of incorporating learning with evolution [… idea to tackle catastrophic forgetting in transfer learning [17] and …
S Khadka, S Majumdar, T Nassar… - … machine learning, 2019 - proceedings.mlr.press
… In this paper, we introduce Collaborative Evolutionary ReinforcementLearning (CERL)… evolutionaryperspective, this is closely related to the idea of incorporating learning with evolution …
MM Drugan - Swarm and evolutionary computation, 2019 - Elsevier
… of ReinforcementLearning (RL) techniques blends with one or more techniques from Evolutionary … techniques as the evolutionary computation versus reinforcementlearning (ECRL) …
DF Hougen, SNH Shah - 2019 IEEE Symposium Series on …, 2019 - ieeexplore.ieee.org
… realms, evolution and reinforcementlearning are parallel … world, evolution is antecedent to all forms of learning but can… , evolutionary computation and reinforcementlearning were …
… From the learningperspective, reinforcementlearning (RL) shows many parallels with how humans and animals can deal with new unknown sequential decision-making tasks. …
… of evolutionaryreinforcementlearning (ERL). ERL [10] is a fusion of EC and reinforcement learning (RL), in which evolutionary techniques (such as genetic algorithms or evolutionary …
S Khadka, K Tumer - Advances in Neural Information …, 2018 - proceedings.neurips.cc
… In this paper, we introduce EvolutionaryReinforcementLearning (… evolutionaryperspective, combining RL with EA is closely related to the idea of incorporating learning with evolution [1…
S Lü, S Han, W Zhou, J Zhang - Information Sciences, 2021 - Elsevier
… We propose Recruitment-imitation Mechanism (RIM) and an evolutionaryreinforcement learning framework that applies this mechanism. At the core of RIM, a dual-policy RL structure is …