A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Kick-motion Training with DQN in AI Soccer Environment
[article]
2022
arXiv
pre-print
Preserved Fulltext
The training based on the RCS is performed with the widely used Deep Q-network (DQN) and tested in the AI Soccer environment implemented with Webots simulation software. ...
This paper presents a technique to train a robot to perform kick-motion in AI soccer by using reinforcement learning (RL). ...
In this paper, we consider training kick-motion with a deep Q-network (DQN). ...
arXiv:2212.00389v1
fatcat:m6qr3merjjc5nftooslyrgofqa
Two-stage training algorithm for AI robot soccer
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The proposed method is applied to 5 versus 5 AI robot soccer for validation. ...
During training, two training processes are conducted in a series. ...
combined with kick, 2 kinds of forward motion combined with kick, stop combined with kick, and stop. ...
arXiv:2104.05931v1
fatcat:rcwszexuovbapi24td56zg433i
Two-stage training algorithm for AI robot soccer
2021
PeerJ Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The proposed method is applied to 5 versus 5 AI robot soccer for validation. The experiments are performed in a robot soccer environment using Webots robot simulation software. ...
Quantitatively, a team trained by the proposed method improves the score concede rate by 5% to 30% when compared to teams trained with the other approaches in matches against evaluation teams. ...
combined with kick, 2 kinds of forward motion combined with kick, stop combined with kick, and stop. ...
doi:10.7717/peerj-cs.718
pmid:34616894
pmcid:PMC8459783
fatcat:gqrijegdbjdhnmd54fulibs7iy
Foosball Table Goalkeeper Automation Using Reinforcement Learning
2021
Lernen, Wissen, Daten, Analysen
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The training is performed in simulation to be transferred to the physical Foosball table for execution. In order to make the training in simulation more robust, we applied domain randomization. ...
Reinforcement learning (RL) is used to learn strategies to autonomously control the goalkeeper rod on a physical Foosball table in an efficient manner. ...
In the work at hand, we are aiming to automate the game of Foosball which is also known as table soccer. ...
dblp:conf/lwa/RohrerSGGH21
fatcat:vx5jgxelqjavhp2z2quhfnydoy
Artificial Intelligence and Robotics
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The global AI market is around 260 billion USD in 2016 and it is estimated to exceed 3 trillion by 2024. ...
Current AI technologies are used in a set area of applications, ranging from healthcare, manufacturing, transport, energy, to financial services, banking, advertising, management consulting and government ...
It brings some certainty in this uncertain time, demonstrating the UK's drive to kick-start disruptive technologies that could transform our economy, with a clear vision for positioning the UK in the international ...
arXiv:1803.10813v1
fatcat:p2czbmak4jcyxbtncqfqlkxtma
Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Despite many advances over the past three decades, learning in many domains still requires a large amount of interaction with the environment, which can be prohibitively expensive in realistic scenarios ...
Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback. ...
Part of this work has taken place in the Learning Agents Research Group (LARG) at the Artificial Intelligence Laboratory, The University of Texas at Austin. LARG re- ...
arXiv:2003.04960v2
fatcat:iacmqeb7jjeezpo27jsnzuqb7u
Interactive Imitation Learning in Robotics: A Survey
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this article, we attempt to facilitate research in IIL and lower entry barriers for new practitioners by providing a survey of the field that unifies and structures it. ...
We organize the most relevant works in IIL in terms of human-robot interaction (i.e., types of feedback), interfaces (i.e., means of providing feedback), learning (i.e., models learned from feedback and ...
also includes the approaches based on ML/AI that have humans in the execution loop, i.e., systems that interact with humans as in ML/AI-based Human-Computer Interaction (HCI) or Human-Robot Interaction ...
arXiv:2211.00600v1
fatcat:g7lrggof7zakro7zrll42r2h6a
Learning and generalizing behaviors for robots from human demonstration
[article]
2020
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This thesis tries to solve the issue with active context selection, active training set selection, surrogate models, and manifold learning. ...
The field is becoming more and more popular in applications where modeling the environment and the robot is cumbersome, difficult, or maybe even impossible. ...
A3C has been evaluated in various Atari 2600 games [Bel+13] and has been shown to clearly outperform DQN with respect to wall-clock training time and final performance. Wang et al. ...
doi:10.26092/elib/382
fatcat:onlwdy6u5zhatjskzimrfzplmy
The targum (1963:Oct. 1 - 1963:Oct. 31)
1963
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In January 1869, the Targum as we now know it, made its appearance as a monthly paper that concerned itself with student "literary contributions" and college news as well as serving as a vehicle for bringing ...
The newspaper has continuously been published since 1869 with the exception of 19 months during the second world war, between February 1944 and October 1945. ...
L anguage train in g in creole. 8. ...
doi:10.7282/t3-jt5a-wg17
fatcat:q64y6puyoremrhm4nd6qsdbph4