Towards High Level Skill Learning: Learn to Return Table Tennis Ball Using Monte-Carlo Based Policy Gradient Method

Table tennis is acyclic, polistructural sports activity which requires a high degree of physical, psychological, technical and tactical preparedness of the athlete. In the function of development and maintenance of functional ability high level, variety of methods impose, apply different training means, methods and loads. In this paper are presented laboratory and field testing results of aerobic functional capabilities of best ping pong players of Serbia and Serbian youth team before the European Championships in Bratislava in 2015, as well as exercises that can be applied in the training process of functional abilities development. Dosage, intensity and exercise selection should depend on the level of athletes physical fitness, and the level of adoption and trained kicks, athletes age, training periodization and etc.

Download Full-text

On the Analysis of the High Level Table Tennis Athletes Special Physical Quality

Advances in Physical Sciences ◽

10.12677/aps.2015.32003 ◽

2015 ◽

Vol 03 (02) ◽

pp. 15-20 ◽

Cited By ~ 1

Author(s):

景文颜

Keyword(s):

Table Tennis ◽

Physical Quality ◽

High Level

Download Full-text

Application of Vibration Testing Technology in Table Tennis Ball Land Point Location

Proceedings of the 2013 International Workshop on Computer Science in Sports ◽

10.2991/iwcss-13.2013.70 ◽

2013 ◽

Author(s):

Meiling Cui ◽

Jian Zhang

Keyword(s):

Tennis Ball ◽

Table Tennis ◽

Vibration Testing ◽

Point Location ◽

Testing Technology

Download Full-text

Inverse design of grating couplers using the policy gradient method from reinforcement learning

Nanophotonics ◽

10.1515/nanoph-2021-0332 ◽

2021 ◽

Vol 0 (0) ◽

Author(s):

Sean Hooten ◽

Raymond G. Beausoleil ◽

Thomas Van Vaerenbergh

Keyword(s):

Neural Network ◽

Reinforcement Learning ◽

Gradient Method ◽

Photonic Devices ◽

Inverse Design ◽

Grating Couplers ◽

Electromagnetic Devices ◽

Policy Gradient ◽

Gradient Based ◽

Local Gradient

Abstract We present a proof-of-concept technique for the inverse design of electromagnetic devices motivated by the policy gradient method in reinforcement learning, named PHORCED (PHotonic Optimization using REINFORCE Criteria for Enhanced Design). This technique uses a probabilistic generative neural network interfaced with an electromagnetic solver to assist in the design of photonic devices, such as grating couplers. We show that PHORCED obtains better performing grating coupler designs than local gradient-based inverse design via the adjoint method, while potentially providing faster convergence over competing state-of-the-art generative methods. As a further example of the benefits of this method, we implement transfer learning with PHORCED, demonstrating that a neural network trained to optimize 8° grating couplers can then be re-trained on grating couplers with alternate scattering angles while requiring >10× fewer simulations than control cases.

Download Full-text