The relationship between uncertainty and affect

EC Anderson, RN Carleton, M Diefenbach… - Frontiers in …, 2019‏ - frontiersin.org
Uncertainty and affect are fundamental and interrelated aspects of the human condition.
Uncertainty is often associated with negative affect, but in some circumstances, it is …

Modular deep reinforcement learning from reward and punishment for robot navigation

J Wang, S Elfwing, E Uchibe - Neural Networks, 2021‏ - Elsevier
Abstract Modular Reinforcement Learning decomposes a monolithic task into several tasks
with sub-goals and learns each one in parallel to solve the original problem. Such learning …

Reinforcement learning algorithms in global path planning for mobile robot

VN Sichkar - 2019 International Conference on Industrial …, 2019‏ - ieeexplore.ieee.org
The paper is devoted to the research of two approaches for global path planning for mobile
robots, based on Q-Learning and Sarsa algorithms. The study has been done with different …

[HTML][HTML] A 2D optimal path planning algorithm for autonomous underwater vehicle driving in unknown underwater canyons

Y Sun, X Luo, X Ran, G Zhang - Journal of Marine Science and …, 2021‏ - mdpi.com
This research aims to solve the safe navigation problem of autonomous underwater vehicles
(AUVs) in deep ocean, which is a complex and changeable environment with various …

Learning failure prevention skills for safe robot manipulation

AC Ak, EE Aksoy, S Sariel - IEEE Robotics and Automation …, 2023‏ - ieeexplore.ieee.org
Robots are more capable of achieving manipulation tasks for everyday activities than before.
However, the safety of manipulation skills that robots employ is still an open problem …

Reward-punishment reinforcement learning with maximum entropy

J Wang, E Uchibe - 2024 International Joint Conference on …, 2024‏ - ieeexplore.ieee.org
We introduce the" soft Deep MaxPain"(softDMP) algorithm, which integrates the optimization
of long-term policy entropy into reward-punishment reinforcement learning objectives. Our …

Improving robot motor learning with negatively valenced reinforcement signals

N Navarro-Guerrero, RJ Lowe, S Wermter - Frontiers in neurorobotics, 2017‏ - frontiersin.org
Both nociception and punishment signals have been used in robotics. However, the
potential for using these negatively valenced types of reinforcement learning signals for …

Vicarious value learning: knowledge transfer through affective processing on a social differential outcomes task

J Rittmo, R Carlsson, P Gander, R Lowe - Acta Psychologica, 2020‏ - Elsevier
The findings of differential outcomes training procedures in controlled stimulus-response
learning settings have been explained through theorizing two processes of response …

Bridging connectionism and relational cognition through bi-directional affective-associative processing

R Lowe, A Almér, C Balkenius - Open Information Science, 2019‏ - degruyter.com
Connectionist architectures constitute a popular method for modelling animal associative
learning processes in order to glean insights into the formation of cognitive capacities. Such …

Affective-Associative Two-Process theory: A neural network investigation of adaptive behaviour in differential outcomes training

R Lowe, E Billing - Adaptive Behavior, 2017‏ - journals.sagepub.com
In this article we present a novel neural network implementation of Associative Two-Process
(ATP) theory based on an Actor–Critic-like architecture. Our implementation emphasizes the …