Interaction in reinforcement learning reduces the need for finely tuned hyperparameters in complex tasks
暂无分享,去创建一个
Chris Stahlhut | Cornelius Weber | Stefan Wermter | Nicolás Navarro-Guerrero | C. Weber | S. Wermter | C. Stahlhut | Nicolás Navarro-Guerrero
[1] Ben J. A. Kröse,et al. Learning from delayed rewards , 1995, Robotics Auton. Syst..
[2] Andrea Lockerd Thomaz,et al. Policy Shaping: Integrating Human Feedback with Reinforcement Learning , 2013, NIPS.
[3] Igor Farkas,et al. Grounding the Meanings in Sensorimotor Behavior using Reinforcement Learning , 2012, Front. Neurorobot..
[4] W. Schultz. Getting Formal with Dopamine and Reward , 2002, Neuron.
[5] D. Shanks,et al. A Re-examination of Probability Matching and Rational Choice , 2002 .
[6] Stefan Wermter,et al. Real-world reinforcement learning for autonomous humanoid robot docking , 2012, Robotics Auton. Syst..
[7] Andrea L. Thomaz,et al. Socially guided machine learning , 2006 .
[8] Gheorghe Leonte Mogan,et al. Obstacle avoidance of redundant manipulators using neural networks based reinforcement learning , 2012 .
[9] Chris Eliasmith,et al. A neural model of hierarchical reinforcement learning , 2017, CogSci.
[10] Richard S. Sutton,et al. Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.
[11] J. Bruner,et al. The role of tutoring in problem solving. , 1976, Journal of child psychology and psychiatry, and allied disciplines.