Stefan Elfwing

22 papers A 3B 1Journal 12Unranked 4

Year	Rank	Type	Title / Venue / Authors
2023	J	`jnl`	Predictive uncertainty estimation for out-of-distribution detection in digital pathology. Medical Image Anal. Jasper Linmans, Stefan Elfwing, Jeroen van der Laak, Geert Litjens
2021	J	`jnl`	Modular deep reinforcement learning from reward and punishment for robot navigation. Neural Networks Jiexin Wang, Stefan Elfwing, Eiji Uchibe
2018	—	`conf`	Deep Reinforcement Learning by Parallelizing Reward and Punishment using the MaxPain Architecture. ICDL-EPIROB Jiexin Wang, Stefan Elfwing, Eiji Uchibe
2018	A	`conf`	Online meta-learning by parallel algorithm competition. GECCO Stefan Elfwing, Eiji Uchibe, Kenji Doya
2018	J	`jnl`	Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Networks Stefan Elfwing, Eiji Uchibe, Kenji Doya
2018	J	`jnl`	Unbounded Output Networks for Classification. CoRR Stefan Elfwing, Eiji Uchibe, Kenji Doya
2017	J	`jnl`	Online Meta-learning by Parallel Algorithm Competition. CoRR Stefan Elfwing, Eiji Uchibe, Kenji Doya
2017	—	`conf`	Parallel reward and punishment control in humans and robots: Safe reinforcement learning using the MaxPain algorithm. ICDL-EPIROB Stefan Elfwing, Ben Seymour
2017	J	`jnl`	Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning. CoRR Stefan Elfwing, Eiji Uchibe, Kenji Doya
2016	J	`jnl`	From free energy to expected energy: Improving energy-based value function approximation in reinforcement learning. Neural Networks Stefan Elfwing, Eiji Uchibe, Kenji Doya
2015	J	`jnl`	Expected energy-based restricted Boltzmann machine for classification. Neural Networks Stefan Elfwing, Eiji Uchibe, Kenji Doya
2013	J	`jnl`	Scaled free-energy based reinforcement learning for robust and efficient learning in high-dimensional state spaces. Frontiers Neurorobotics Stefan Elfwing, Eiji Uchibe, Kenji Doya
2011	J	`jnl`	Darwinian embodied evolution of the learning ability for survival. Adapt. Behav. Stefan Elfwing, Eiji Uchibe, Kenji Doya, Henrik I. Christensen
2010	—	`conf`	Free-Energy Based Reinforcement Learning for Vision-Based Navigation with High-Dimensional Sensory Inputs. ICONIP (1) Stefan Elfwing, Makoto Otsuka, Eiji Uchibe, Kenji Doya
2009	—	`ch.`	Co-evolution of Rewards and Meta-parameters in Embodied Evolution. Creating Brain-Like Intelligence Stefan Elfwing, Eiji Uchibe, Kenji Doya
2009	—	`conf`	Emergence of Different Mating Strategies in Artificial Embodied Evolution. ICONIP (2) Stefan Elfwing, Eiji Uchibe, Kenji Doya
2008	J	`jnl`	Co-evolution of Shaping Rewards and Meta-Parameters in Reinforcement Learning. Adapt. Behav. Stefan Elfwing, Eiji Uchibe, Kenji Doya, Henrik I. Christensen
2007	—	`—`	Embodied Evolution of Learning Ability. Stefan Elfwing
2007	J	`jnl`	Evolutionary Development of Hierarchical Learning Structures. IEEE Trans. Evol. Comput. Stefan Elfwing, Eiji Uchibe, Kenji Doya, Henrik I. Christensen
2005	B	`conf`	Biologically inspired embodied evolution of survival. Congress on Evolutionary Computation Stefan Elfwing, Eiji Uchibe, Kenji Doya, Henrik I. Christensen
2004	A	`conf`	Multi-agent reinforcement learning: using macro actions to learn a mating task. IROS Stefan Elfwing, Eiji Uchibe, Kenji Doya, Henrik I. Christensen
2003	A	`conf`	An Evolutionary Approach to Automatic Construction of the Structure in Hierarchical Reinforcement Learning. GECCO Stefan Elfwing, Eiji Uchibe, Kenji Doya