Automatic ship collision avoidance using deep reinforcement learning with LSTM in continuous action spaces
Sign Up to like & getrecommendations! Published in 2020 at "Journal of Marine Science and Technology"
DOI: 10.1007/s00773-020-00755-0
Abstract: This paper presents an automatic collision avoidance algorithm for ships using a deep reinforcement learning (DRL) in continuous action spaces. Obstacle zone by target (OZT) is used to compute an area where a collision will… read more here.
Keywords: collision; collision avoidance; action spaces; continuous action ... See more keywords
Orthogonal Adversarial Deep Reinforcement Learning for Discrete- and Continuous-Action Problems
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Access"
DOI: 10.1109/access.2024.3479089
Abstract: Recent advancements in deep neural network (DNN) technology are enhancing the utilities of machine learning and meeting potential demands for real-world applications. Deep reinforcement learning (DRL) is a key component in realizing complex decision-making and… read more here.
Keywords: deep reinforcement; continuous action; discrete continuous; reinforcement learning ... See more keywords
Feedback of action outcome retrospectively influences sense of agency in a continuous action task
Sign Up to like & getrecommendations! Published in 2018 at "PLoS ONE"
DOI: 10.1371/journal.pone.0202690
Abstract: Here, we investigated whether explicit feedback on the result of the action (success or failure) modified sense of agency (SoA) in a continuous action task. Participants carried a white dot with a delay to a… read more here.
Keywords: action task; continuous action; sense agency; action ... See more keywords