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
Neural-Symbolic Learning: How to Play Soccer
2011
International Workshop on Neural-Symbolic Learning and Reasoning
Preserved Fulltext
The purpose of this simulator is to test our neural symbolic approach towards normative reasoning. ...
To be more precise, the case study regards RoboCup scenario. ...
The coach gives directions to the robot about how they should play during the match. ...
dblp:conf/nesy/Tosatto11
fatcat:gfeym5gyivcxxfdb4lextyazta
Braid: Weaving Symbolic and Neural Knowledge into Coherent Logical Explanations
[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.
Other Versions
We use a simple QA example from a children's story to motivate Braid's design and explain how the various components work together to produce a coherent logical explanation. ...
Traditional symbolic reasoning engines, while attractive for their precision and explicability, have a few major drawbacks: the use of brittle inference procedures that rely on exact matching (unification ...
Figure 5: GLUCOSE suggestion for a story about soccer. ...
arXiv:2011.13354v4
fatcat:7p53rr37nrbznk2vc644u6lg44
Reasoning in Non-Probabilistic Uncertainty: Logic Programming and Neural-Symbolic Computing as Examples
[article]
2017
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
of the intended model, and a neural-symbolic implementation of Input/Output logic for dealing with uncertainty in dynamic normative contexts. ...
This article aims to achieve two goals: to show that probability is not the only way of dealing with uncertainty (and even more, that there are kinds of uncertainty which are for principled reasons not ...
Acknowledgements We want to thank the following people for their indispensable contributions to different parts of the work reported in this article: Guido Boella, Silvano Colombo Tosatto, Valerio Genovese ...
arXiv:1701.05226v2
fatcat:eg67ppsao5cmvnxv5s5vquchma
Braid: Weaving Symbolic and Neural Knowledge into Coherent Logical Explanations
2022
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
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.
We use a simple QA example from a children's story to motivate Braid's design and explain how the various components work together to produce a coherent logical explanation. ...
Traditional symbolic reasoning engines, while attractive for their precision and explicability, have a few major drawbacks: the use of brittle inference procedures that rely on exact matching (unification ...
Instead of a pure neural approach, we developed a hybrid neuro-symbolic solution to this problem using Braid, one that is capable of giving an explanation for choosing a particular story ending. ...
doi:10.1609/aaai.v36i10.21333
fatcat:lcsfd6dtzvcbvdif47htr7jowu
Reasoning in Non-probabilistic Uncertainty: Logic Programming and Neural-Symbolic Computing as Examples
2017
Minds and Machines
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 2018; you can also visit the original URL.
The file type is application/pdf.
of the intended model, and a neural-symbolic implementation of input/output logic for dealing with uncertainty in dynamic normative contexts. ...
This article aims to achieve two goals: to show that probability is not the only way of dealing with uncertainty (and even more, that there are kinds of uncertainty which are for principled reasons not ...
Acknowledgements We want to thank the following people for their indispensable contributions to different parts of the work reported in this article: Guido Boella, Silvano Colombo Tosatto, Valerio Genovese ...
doi:10.1007/s11023-017-9428-3
fatcat:unbwsv3civd45hivgh5xpuzlzu
Opponent Modeling in Deep Reinforcement Learning
[article]
2016
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.
Inspired by the recent success of deep reinforcement learning, we present neural-based models that jointly learn a policy and the behavior of opponents. ...
We evaluate our models on a simulated soccer game and a popular trivia game, showing superior performance over DQN and its variants. ...
; and losing players play more to learn an adaptive policy. ...
arXiv:1609.05559v1
fatcat:bd6p7tzhk5cuhpl4nwtjfwemdi
End-to-End Deep Imitation Learning: Robot Soccer Case Study
[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.
In this work, we use imitation learning to teach the robot to dribble the ball to the goal. ...
In 3D realistic robotics simulator experiments, we show that the robot is able to learn to search the ball and dribble the ball, but it struggles to align to the goal. ...
Let's consider the problem of high-level behavior (task) learning such as learning to play soccer. ...
arXiv:1807.09205v1
fatcat:lhcgz24v3fegpliflgrojrzvoe
Robot Action Selection Learning via Layered Dimension Informed Program Synthesis
[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
Action selection policies (ASPs), used to compose low-level robot skills into complex high-level tasks are commonly represented as neural networks (NNs) in the state of the art. ...
We present empirical results to demonstrate that LDIPS 1) can synthesize effective ASPs for robot soccer and autonomous driving domains, 2) requires two orders of magnitude fewer training examples than ...
Alternatively, synthesis has been used to guide learning, as in work that composes neural perception and symbolic program execution to jointly learn visual concepts, words, and semantic parsing of questions ...
arXiv:2008.04133v2
fatcat:llmbk5qvr5a77hxdwhcsio7gde
The new wave in robot learning
1997
Robotics and Autonomous Systems
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 2017; you can also visit the original URL.
The file type is application/pdf.
In response, cognitivists have suggested connecting the symbol system to the world via transducers [34] . ...
Cognition mind and intelligence have been studied in vacuo as a glass box in a black world (as opposed to behaviorism which is about a black box in a transparent world) -the physical symbol system hypothesis ...
Thanks to Tom Ziemke and Amanda Sharkey for helpful comments on an earlier draft. Finally, I would like to thank Professor Frans Groen and the staff at Elsevier for their support and patience. ...
doi:10.1016/s0921-8890(97)00037-7
fatcat:djccntadlze43drzdi3lipssgm
New reinforcement learning algorithm for robot soccer
2017
ORiON
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 2018; you can also visit the original URL.
The file type is application/pdf.
Reinforcement Learning (RL) is a powerful technique to develop intelligent agents in the field of Artificial Intelligence (AI). ...
Six scenarios were defined to develop shooting skills for an SSL soccer robot in various situations using the proposed algorithm. ...
Summary and conclusion In this research, reinforcement learning (RL) was applied to develop basic soccer skills for soccer robots playing in the RoboCup Small Size League. ...
doi:10.5784/33-1-542
fatcat:5wok6pag5zbsph7eaz6223hf4e
Cognitive learning and the multimodal memory game: Toward human-level machine learning
2008
2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)
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 2011; you can also visit the original URL.
The file type is application/pdf.
Concrete experimental results are presented to illustrate the usefulness of the game and the cognitive learning framework for studying human-level learning and intelligence. 3261 978-1-4244-1821-3/08/$25.00 ...
In particular, we suggest two fundamental principles to achieve human-level machine learning: continuity (forming a lifelong memory continuously) and glocality (organizing a plastic structure of localized ...
Connectionist models or neural networks are not suitable to model this kind of learning. ...
doi:10.1109/ijcnn.2008.4634261
dblp:conf/ijcnn/Zhang08
fatcat:k6ifhx3cbndk3nn7goqckaqupi
Fuzzy behaviour learning for sony legged robots
2001
European Society for Fuzzy Logic and Technology
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 2017; you can also visit the original URL.
The file type is application/pdf.
This paper presents a learning reactive control scheme for the Sony legged robots to play soccer. ...
The learning of a FLC is conducted in two stages:learning parameters by GA and learnign its structure by Q-learning. ...
The reactive behaviors used to play soccer are based on this set of primitive behaviors and encoded by FLCs. ...
dblp:conf/eusflat/GuH01
fatcat:kdk55tkvbvaljdtjzgr3ovi27e
Learning from Humans
[chapter]
2016
Springer Handbook of Robotics
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 2019; you can also visit the original URL.
The file type is application/pdf.
This chapter surveys the main approaches developed to date to endow robots with the ability to learn from human guidance. ...
We then review algorithmic approaches to model skills individually and as a compound and algorithms that combine learning from human guidance with reinforcement learning. ...
In [74.52] , a robot dog is taught to play soccer by a human guiding it via a joystick. ...
doi:10.1007/978-3-319-32552-1_74
fatcat:wtcftkgkwveexpfbmnkcebi5wu
Deep Reinforcement Learning
[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.
Then we discuss important mechanisms for RL, including attention and memory, unsupervised learning, hierarchical RL, multi-agent RL, relational RL, and learning to learn. ...
We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources. ...
Lanctot et al. (2017) observe that independent RL, in which each agent learns by interacting with the environment, oblivious to other agents, can overfit the learned policies to other agents' policies ...
arXiv:1810.06339v1
fatcat:kp7atz5pdbeqta352e6b3nmuhy
A Survey on Transfer Learning for Multiagent Reinforcement Learning Systems
2019
The Journal of Artificial Intelligence Research
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 2019; you can also visit the original URL.
The file type is application/pdf.
However, learning a complex task from scratch is impractical due to the huge sample complexity of RL algorithms. ...
Multiagent Reinforcement Learning (RL) solves complex tasks that require coordination with other agents through autonomous exploration of the environment. ...
This work was partially carried out while the first author was affiliated to the Learning Agents Research Group (LARG) at the University of Texas at Austin, TX, USA. ...
doi:10.1613/jair.1.11396
fatcat:mn4gw6oh5zgszl6l53fgesei5i
« Previous
Showing results 1 — 15 out of 1,734 results