scholarly journals A novel paradigm for auditory discrimination training with social reinforcement in songbirds

2014 ◽  
Author(s):  
Kirill Tokarev ◽  
Ofer Tchernichovski
Keyword(s):  
Reinforcement Learning ◽  
Vocal Communication ◽  
Auditory Stimuli ◽  
Social Reinforcement ◽  
Training Procedure ◽  
Zebra Finches ◽  
Juvenile Male ◽  
Visual Contact ◽  
Training Apparatus ◽  
Auditory Discrimination Training

Zebra finches are a highly social, gregarious, species and eagerly engage in vocal communication. We have developed a training apparatus that allows training zebra finches to discriminate socially reinforced and aversive vocal stimuli. In our experiments, juvenile male zebra finches were trained to discriminate a song that was followed by a brief air puff (aversive) and a song that allowed them to stay in visual contact with another bird, 'audience' (social song). During training, the birds learned quickly to avoid air puffs by escaping the aversive song within 2 sec. They escaped significantly more aversive songs than socially reinforced ones, and this effect grew stronger with the number of training sessions. Therefore, we propose this training procedure as an effective method to teach zebra finches to discriminate between different auditory stimuli, which may also be used as a broader paradigm for addressing social reinforcement learning. The apparatus can be built from commercially available parts, and we are sharing the software on our website.

scholarly journals Stability Control of a Biped Robot on a Dynamic Platform Based on Hybrid Reinforcement Learning

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4468
Author(s):  
Ao Xi ◽  
Chao Chen
Keyword(s):  
Reinforcement Learning ◽  
Center Of Pressure ◽  
Stable State ◽  
Biped Robot ◽  
Action Space ◽  
Training Procedure ◽  
Joint Angles ◽  
Model Free ◽  
Initial Control ◽  
Hybrid Reinforcement

In this work, we introduced a novel hybrid reinforcement learning scheme to balance a biped robot (NAO) on an oscillating platform, where the rotation of the platform is considered as the external disturbance to the robot. The platform had two degrees of freedom in rotation, pitch and roll. The state space comprised the position of center of pressure, and joint angles and joint velocities of two legs. The action space consisted of the joint angles of ankles, knees, and hips. By adding the inverse kinematics techniques, the dimension of action space was significantly reduced. Then, a model-based system estimator was employed during the offline training procedure to estimate the dynamics model of the system by using novel hierarchical Gaussian processes, and to provide initial control inputs, after which the reduced action space of each joint was obtained by minimizing the cost of reaching the desired stable state. Finally, a model-free optimizer based on DQN (λ) was introduced to fine tune the initial control inputs, where the optimal control inputs were obtained for each joint at any state. The proposed reinforcement learning not only successfully avoided the distribution mismatch problem, but also improved the sample efficiency. Simulation results showed that the proposed hybrid reinforcement learning mechanism enabled the NAO robot to balance on an oscillating platform with different frequencies and magnitudes. Both control performance and robustness were guaranteed during the experiments.

scholarly journals Application of Reinforcement Learning to a Robotic Drinking Assistant

Robotics ◽  
2019 ◽  
Vol 9 (1) ◽  
pp. 1 ◽  
Author(s):  
Tejas Kumar Shastha ◽  
Maria Kyrarini ◽  
Axel Gräser
Keyword(s):  
Reinforcement Learning ◽  
Tactile Feedback ◽  
Human Robot Interaction ◽  
Assistive Robotics ◽  
Training Procedure ◽  
Assistive Robots ◽  
Assistive Robot ◽  
Markov Decision ◽  
Degree Of Acceptance ◽  
High Degree

Meal assistant robots form a very important part of the assistive robotics sector since self-feeding is a priority activity of daily living (ADL) for people suffering from physical disabilities like tetraplegia. A quick survey of the current trends in this domain reveals that, while tremendous progress has been made in the development of assistive robots for the feeding of solid foods, the task of feeding liquids from a cup remains largely underdeveloped. Therefore, this paper describes an assistive robot that focuses specifically on the feeding of liquids from a cup using tactile feedback through force sensors with direct human–robot interaction (HRI). The main focus of this paper is the application of reinforcement learning (RL) to learn what the best robotic actions are, based on the force applied by the user. A model of the application environment is developed based on the Markov decision process and a software training procedure is designed for quick development and testing. Five of the commonly used RL algorithms are investigated, with the intention of finding the best fit for training, and the system is tested in an experimental study. The preliminary results show a high degree of acceptance by the participants. Feedback from the users indicates that the assistive robot functions intuitively and effectively.

Maximized song learning of juvenile male zebra finches following BDNF expression in the HVC

2013 ◽  
Vol 38 (9) ◽  
pp. 3338-3344 ◽  
Author(s):  
Falk Dittrich ◽  
Andries ter Maat ◽  
Rene F. Jansen ◽  
Anton Pieneman ◽  
Moritz Hertel ◽  
...  
Keyword(s):  
Song Learning ◽  
Zebra Finches ◽  
Juvenile Male ◽  
Bdnf Expression

Racial Bias Shapes Social Reinforcement Learning

2014 ◽  
Vol 25 (3) ◽  
pp. 711-719 ◽  
Author(s):  
Björn Lindström ◽  
Ida Selbing ◽  
Tanaz Molapour ◽  
Andreas Olsson
Keyword(s):  
Reinforcement Learning ◽  
Racial Bias ◽  
Social Reinforcement

Vocal communication at the nest between mates in wild zebra finches: a private vocal duet?

2010 ◽  
Vol 80 (4) ◽  
pp. 597-605 ◽  
Author(s):  
Julie E. Elie ◽  
Mylène M. Mariette ◽  
Hédi A. Soula ◽  
Simon C. Griffith ◽  
Nicolas Mathevon ◽  
...  
Keyword(s):  
Vocal Communication ◽  
Zebra Finches

Functional changes in field L complex during song development of juvenile male zebra finches

2000 ◽  
Vol 125 (1-2) ◽  
pp. 153-165 ◽  
Author(s):  
Daniel D Gehr ◽  
Sonja B Hofer ◽  
Dominik Marquardt ◽  
Hans-Joachim Leppelsack
Keyword(s):  
Zebra Finches ◽  
Juvenile Male ◽  
Functional Changes ◽  
Field L ◽  
Song Development

scholarly journals Routing of Electric Vehicles With Intermediary Charging Stations: A Reinforcement Learning Approach

2021 ◽  
Vol 4 ◽  
Author(s):  
Marina Dorokhova ◽  
Christophe Ballif ◽  
Nicolas Wyrsch
Keyword(s):  
Reinforcement Learning ◽  
Electric Vehicles ◽  
Mathematical Formulation ◽  
Route Planning ◽  
Learning Approach ◽  
Training Procedure ◽  
Routing Problem ◽  
Policy Model ◽  
Model Free ◽  
Charging Stations

In the past few years, the importance of electric mobility has increased in response to growing concerns about climate change. However, limited cruising range and sparse charging infrastructure could restrain a massive deployment of electric vehicles (EVs). To mitigate the problem, the need for optimal route planning algorithms emerged. In this paper, we propose a mathematical formulation of the EV-specific routing problem in a graph-theoretical context, which incorporates the ability of EVs to recuperate energy. Furthermore, we consider a possibility to recharge on the way using intermediary charging stations. As a possible solution method, we present an off-policy model-free reinforcement learning approach that aims to generate energy feasible paths for EV from source to target. The algorithm was implemented and tested on a case study of a road network in Switzerland. The training procedure requires low computing and memory demands and is suitable for online applications. The results achieved demonstrate the algorithm’s capability to take recharging decisions and produce desired energy feasible paths.

scholarly journals MAPS: Multi-Agent reinforcement learning-based Portfolio management System.

2020 ◽  
Author(s):  
Jinho Lee ◽  
Raehyun Kim ◽  
Seok-Won Yi ◽  
Jaewoo Kang
Keyword(s):  
Deep Learning ◽  
Reinforcement Learning ◽  
Portfolio Management ◽  
Management System ◽  
Investment Strategy ◽  
Sharpe Ratio ◽  
Training Procedure ◽  
Learning Methods ◽  
Multi Agent ◽  
Diversified Portfolio

Generating an investment strategy using advanced deep learning methods in stock markets has recently been a topic of interest. Most existing deep learning methods focus on proposing an optimal model or network architecture by maximizing return. However, these models often fail to consider and adapt to the continuously changing market conditions. In this paper, we propose the Multi-Agent reinforcement learning-based Portfolio management System (MAPS). MAPS is a cooperative system in which each agent is an independent "investor" creating its own portfolio. In the training procedure, each agent is guided to act as diversely as possible while maximizing its own return with a carefully designed loss function. As a result, MAPS as a system ends up with a diversified portfolio. Experiment results with 12 years of US market data show that MAPS outperforms most of the baselines in terms of Sharpe ratio. Furthermore, our results show that adding more agents to our system would allow us to get a higher Sharpe ratio by lowering risk with a more diversified portfolio.

Sign in / Sign up

Export Citation Format

Share Document