| Sigmoid-weighted linear units for neural network function approximation in reinforcement learning S Elfwing, E Uchibe, K Doya Neural networks 107, 3-11, 2018 | 1855 | 2018 |
| Modular deep reinforcement learning from reward and punishment for robot navigation J Wang, S Elfwing, E Uchibe Neural Networks 135, 115-126, 2021 | 56 | 2021 |
| Biologically inspired embodied evolution of survival S Elfwing, E Uchibe, K Doya, HI Christensen 2005 IEEE Congress on Evolutionary Computation 3, 2210-2216, 2005 | 54 | 2005 |
| Predictive uncertainty estimation for out-of-distribution detection in digital pathology J Linmans, S Elfwing, J van der Laak, G Litjens Medical Image Analysis 83, 102655, 2023 | 51 | 2023 |
| Evolutionary development of hierarchical learning structures S Elfwing, E Uchibe, K Doya, HI Christensen IEEE transactions on evolutionary computation 11 (2), 249-264, 2007 | 49 | 2007 |
| Expected energy-based restricted Boltzmann machine for classification S Elfwing, E Uchibe, K Doya Neural networks 64, 29-38, 2015 | 44 | 2015 |
| Darwinian embodied evolution of the learning ability for survival S Elfwing, E Uchibe, K Doya, HI Christensen Adaptive Behavior 19 (2), 101-120, 2011 | 35 | 2011 |
| Co-evolution of shaping rewards and meta-parameters in reinforcement learning S Elfwing, E Uchibe, K Doya, HI Christensen Adaptive Behavior 16 (6), 400-412, 2008 | 34 | 2008 |
| Parallel reward and punishment control in humans and robots: Safe reinforcement learning using the MaxPain algorithm S Elfwing, B Seymour 2017 Joint IEEE International Conference on Development and Learning and …, 2017 | 32 | 2017 |
| Multi-agent reinforcement learning: Using macro actions to learn a mating task S Elfwing, E Uchibe, K Doya, HI Christensen 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2004 | 29 | 2004 |
| Online meta-learning by parallel algorithm competition S Elfwing, E Uchibe, K Doya Proceedings of the Genetic and Evolutionary Computation Conference, 426-433, 2018 | 27 | 2018 |
| Embodied evolution of learning ability S Elfwing KTH, 2007 | 25 | 2007 |
| From free energy to expected energy: Improving energy-based value function approximation in reinforcement learning S Elfwing, E Uchibe, K Doya Neural Networks 84, 17-27, 2016 | 20 | 2016 |
| Scaled free-energy based reinforcement learning for robust and efficient learning in high-dimensional state spaces S Elfwing, E Uchibe, K Doya Frontiers in neurorobotics 7, 3, 2013 | 19 | 2013 |
| Emergence of polymorphic mating strategies in robot colonies S Elfwing, K Doya PloS one 9 (4), e93622, 2014 | 18 | 2014 |
| An evolutionary approach to automatic construction of the structure in hierarchical reinforcement learning S Elfwing, E Uchibe, K Doya Genetic and Evolutionary Computation—GECCO 2003: Genetic and Evolutionary …, 2003 | 15 | 2003 |
| Free-energy based reinforcement learning for vision-based navigation with high-dimensional sensory inputs S Elfwing, M Otsuka, E Uchibe, K Doya Neural Information Processing. Theory and Algorithms: 17th International …, 2010 | 10 | 2010 |
| A deep neural network–based decision support tool for the detection of lymph node metastases in colorectal cancer specimens C Kindler, S Elfwing, J Öhrvik, M Nikberg Modern Pathology 36 (2), 100015, 2023 | 9 | 2023 |
| Deep reinforcement learning by parallelizing reward and punishment using the maxpain architecture J Wang, S Elfwing, E Uchibe 2018 Joint IEEE 8th International Conference on Development and Learning and …, 2018 | 9 | 2018 |
| Co-evolution of rewards and meta-parameters in embodied evolution S Elfwing, E Uchibe, K Doya Creating Brain-Like Intelligence: From Basic Principles to Complex …, 2009 | 3 | 2009 |
Kenji DoyaOkinawa Institute of Science and TechnologyVerified email at oist.jp