Interactive imitation learning in robotics: A survey

C Celemin, R Pérez-Dattari, E Chisari… - … and Trends® in …, 2022‏ - nowpublishers.com
Interactive Imitation Learning in Robotics: A Survey Page 1 Interactive Imitation Learning in
Robotics: A Survey Page 2 Other titles in Foundations and Trends® in Robotics A Survey on …

An interactive framework for learning continuous actions policies based on corrective feedback

C Celemin, J Ruiz-del-Solar - Journal of Intelligent & Robotic Systems, 2019‏ - Springer
The main goal of this article is to present COACH (COrrective Advice Communicated by
Humans), a new learning framework that allows non-expert humans to advise an agent …

Training an actor-critic reinforcement learning controller for arm movement using human-generated rewards

KM Jagodnik, PS Thomas… - … on Neural Systems …, 2017‏ - ieeexplore.ieee.org
Functional Electrical Stimulation (FES) employs neuroprostheses to apply electrical current
to the nerves and muscles of individuals paralyzed by spinal cord injury to restore voluntary …

Hierarchical control of traffic signals using Q-learning with tile coding

M Abdoos, N Mozayani, ALC Bazzan - Applied intelligence, 2014‏ - Springer
Multi-agent systems are rapidly growing as powerful tools for Intelligent Transportation
Systems (ITS). It is desirable that traffic signals control, as a part of ITS, is performed in a …

Leveraging sub-optimal data for human-in-the-loop reinforcement learning

C Muslimani, ME Taylor - ar** humans in the loop: Teaching via feedback in continuous action space environments
I Sheidlower, A Moore, E Short - 2022 IEEE/RSJ International …, 2022‏ - ieeexplore.ieee.org
Interactive Reinforcement Learning (IntRL) allows human teachers to accelerate the
learning process of Reinforcement Learning (RL) robots. However, IntRL has largely been …

Probabilistic neural network training procedure based on Q(0)-learning algorithm in medical data classification

M Kusy, R Zajdel - Applied Intelligence, 2014‏ - Springer
In this article, an iterative procedure is proposed for the training process of the probabilistic
neural network (PNN). In each stage of this procedure, the Q (0)-learning algorithm is …

Real-time prediction learning for the simultaneous actuation of multiple prosthetic joints

PM Pilarski, TB Dick, RS Sutton - 2013 IEEE 13th International …, 2013‏ - ieeexplore.ieee.org
Integrating learned predictions into a prosthetic control system promises to enhance multi-
joint prosthesis use by amputees. In this article, we present a preliminary study of different …

Learning from demonstrations and human evaluative feedbacks: Handling sparsity and imperfection using inverse reinforcement learning approach

N Mourad, A Ezzeddine, B Nadjar Araabi… - Journal of …, 2020‏ - Wiley Online Library
Programming by demonstrations is one of the most efficient methods for knowledge transfer
to develop advanced learning systems, provided that teachers deliver abundant and correct …