Sigmoid-weighted linear units for neural network function approximation in reinforcement learning von Elfwing, Stefan, Uchibe, Eiji, Doya, Kenji

Volltext

Model-Free Deep Inverse Reinforcement Learning by Logistic Regression von Uchibe, Eiji

Volltext

Forward and inverse reinforcement learning sharing network weights and hyperparameters von Uchibe, Eiji, Doya, Kenji

Volltext

Deep learning, reinforcement learning, and world models von Matsuo, Yutaka, LeCun, Yann, Sahani, Maneesh, Precup, Doina, Silver, David, Sugiyama, Masashi, Uchibe, Eiji, Morimoto, Jun

Volltext

Cooperative and Competitive Reinforcement and Imitation Learning for a Mixture of Heterogeneous Learning Modules von Uchibe, Eiji

Volltext

Constrained Deep Q-Learning Gradually Approaching Ordinary Q-Learning von Ohnishi, Shota, Uchibe, Eiji, Yamaguchi, Yotaro, Nakanishi, Kosuke, Yasui, Yuji, Ishii, Shin

Volltext

From free energy to expected energy: Improving energy-based value function approximation in reinforcement learning von Elfwing, Stefan, Uchibe, Eiji, Doya, Kenji

Volltext

Estimating cost function of expert players in differential games: A model-based method and its data-driven extension von Asl, Hamed Jabbari, Uchibe, Eiji

Volltext

Inverse reinforcement learning methods for linear differential games von Asl, Hamed Jabbari, Uchibe, Eiji

Volltext

Online estimation of objective function for continuous-time deterministic systems von Asl, Hamed Jabbari, Uchibe, Eiji

Volltext

Model-Based Imitation Learning Using Entropy Regularization of Model and Policy von Uchibe, Eiji

Volltext

Adaptive Baseline Enhances EM-Based Policy Search: Validation in a View-Based Positioning Task of a Smartphone Balancer von Wang, Jiexin, Uchibe, Eiji, Doya, Kenji

Volltext

Modular deep reinforcement learning from reward and punishment for robot navigation von Wang, Jiexin, Elfwing, Stefan, Uchibe, Eiji

Volltext

Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning von Morimura, Tetsuro, Uchibe, Eiji, Yoshimoto, Junichiro, Peters, Jan, Doya, Kenji

Volltext

Online Reinforcement Learning Control of Nonlinear Dynamic Systems: A State-action Value Function Based Solution von Asl, Hamed Jabbari, Uchibe, Eiji

Volltext

Deep reinforcement learning with smooth policy update: Application to robotic cloth manipulation von Tsurumine, Yoshihisa, Cui, Yunduan, Uchibe, Eiji, Matsubara, Takamitsu

Volltext

Reinforcement learning-based optimal control of unknown constrained-input nonlinear systems using simulated experience von Asl, Hamed Jabbari, Uchibe, Eiji

Volltext

EM-based policy hyper parameter exploration: application to standing and balancing of a two-wheeled smartphone robot von Wang, Jiexin, Uchibe, Eiji, Doya, Kenji

Volltext

Generative Imitation Learning using Forward and Inverse Reinforcement Learning von Uchibe, Eiji

Volltext

Darwinian embodied evolution of the learning ability for survival von Elfwing, Stefan, Uchibe, Eiji, Doya, Kenji, Christensen, Henrik I

Volltext