Results 21 to 30 of about 5,876,040 (331)
Sensors, 2023 Reinforcement learning agents that have not been seen during training must be robust in test environments. However, the generalization problem is challenging to solve in reinforcement learning using high-dimensional images as the input. The addition of a
Sanghoon Park +4 more
doaj +1 more source
Advanced Engineering Materials, EarlyView., 2023 A novel method for tracking structural changes in gels using widely accessible microcomputed tomography is presented and validated for various hydro‐, alco‐, and aerogels. The core idea of the method is to track positions of micrometer‐sized tracer particles entrapped in the gel and relate them to the density of the gel network.
Anja Hajnal +3 more
wiley +1 more source
A Survey on Reinforcement Learning Methods in Bionic Underwater Robots
Biomimetics, 2023 Bionic robots possess inherent advantages for underwater operations, and research on motion control and intelligent decision making has expanded their application scope.
Ru Tong +5 more
doaj +1 more source
Apress, 2018 The discussion here considers a much more common learning condition where an agent, such as a human or a robot, has to learn to make decisions in the environment from simple feedback. Such feedback is provided only after periods of actions in the form of
F. Wörgötter, B. Porr
semanticscholar +1 more source
Rainbow: Combining Improvements in Deep Reinforcement Learning [PDF]
AAAI Conference on Artificial Intelligence, 2017 The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions to the DQN
Matteo Hessel +9 more
semanticscholar +1 more source
Champion-level drone racing using deep reinforcement learning
Nature, 2023 An autonomous system is described that combines deep reinforcement learning with onboard sensors collecting data from the physical world, enabling it to fly faster than human world champion drone pilots around a race track.
Elia Kaufmann +5 more
semanticscholar +1 more source
Deep Reinforcement Learning for Autonomous Driving: A Survey [PDF]
IEEE transactions on intelligent transportation systems (Print), 2020 With the development of deep representation learning, the domain of reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments.
B. R. Kiran +6 more
semanticscholar +1 more source
Review of Model-Based Reinforcement Learning
Jisuanji kexue yu tansuo, 2020 Deep reinforcement learning (DRL) as an important learning paradigm in the field of machine learning, has received increasing attentions after AlphaGo defeats the human.
ZHAO Tingting, KONG Le, HAN Yajie, REN Dehua, CHEN Yarui
doaj +1 more source
A neural network model for the orbitofrontal cortex and task space acquisition during reinforcement learning. [PDF]
PLoS Computational Biology, 2018 Reinforcement learning has been widely used in explaining animal behavior. In reinforcement learning, the agent learns the value of the states in the task, collectively constituting the task state space, and uses the knowledge to choose actions and ...
Zhewei Zhang +4 more
doaj +1 more source
Algorithms, 2020 Reinforcement learning, as a branch of machine learning, has been gradually applied in the control field. However, in the practical application of the algorithm, the hyperparametric approach to network settings for deep reinforcement learning still ...
Menglin Li +3 more
doaj +1 more source