Results 41 to 50 of about 6,944,236 (307)

Time representation in reinforcement learning models of the basal ganglia [PDF]

, 2013
Reinforcement learning (RL) models have been influential in understanding many aspects of basal ganglia function, from reward prediction to action selection.
Sebastian eDupraz, Samuel Joseph Gershman, Ahmed A. Moustafa, Santiago eQuiroga, Ludvig, Elliot Andrew, Oksdath Mansilla, Mariana, Fernández, Marisa Mariel, Moustafa, Ahmed A., Nieto Guil, Alvaro Fernando, Maria Eugenia Bernis, Emilio L. Malchiodi, Gershman, Samuel J., Sebastián Dupraz, Silvana B. Rosso, Rosso, Silvana Beatriz, Elliot A. Ludvig, Malchiodi, Emilio Luis, Santiago Quiroga, Dupraz, Sebastian, Enrique, Mariana eOksdath, Alvaro Nieto Guil, Samuel J. Gershman, Alvaro F. Nieto Guil, María E. Bernis, Quiroga, Santiago, Marisa M. Fernandez, Ludvig, Elliot A., Moustafa, Ahmed A. (R17078), Bernis, Maria Eugenia, Mariana Oksdath   +29 more
core   +1 more source

Reinforcement-Learning-Based IDS for 6LoWPAN

, 2021
The Routing Protocol for low power Lossy networks (RPL) is a critical operational component of low power wireless personal area networks using IPv6 (6LoWPANs).
Aryan Mohammadi Pasikhani (11456185), Andrew John Clark (4665682), Prosanta Gope (7323521)   +2 more
core   +1 more source

Geometric Reinforcement Learning for Robotic Manipulation

IEEE Access, 2023
Reinforcement learning (RL) is a popular technique that allows an agent to learn by trial and error while interacting with a dynamic environment.
Naseem Alhousani, Matteo Saveriano, Ibrahim Sevinc, Talha Abdulkuddus, Hatice Kose, Fares J. Abu-Dakka   +5 more
doaj   +1 more source

Reinforcement learning in populations of spiking neurons [PDF]

, 2008
Population coding is widely regarded as a key mechanism for achieving reliable behavioral responses in the face of neuronal variability. But in standard reinforcement learning a flip-side becomes apparent.
Urbanczik, R, Walter Senn, Robert Urbanczik, Senn, W, Urbanczik R, Urbanczik, Robert, Senn W   +6 more
core   +1 more source

Reinforcement Learning Approach for Efficient Inventory Policy in Multi-Echelon Supply Chain Under Various Assumptions and Constraints

Journal of Information Systems Engineering and Business Intelligence, 2021
Background: Inventory policy highly influences Supply Chain Management (SCM) process. Evidence suggests that almost half of SCM costs are set off by stock-related expenses. Objective: This paper aims to minimise total inventory cost in SCM by applying a
Ika Nurkasanah
doaj   +1 more source

Sauté RL: Almost Surely Safe Reinforcement Learning Using State Augmentation [PDF]

, 2022
Satisfying safety constraints almost surely (or with probability one) can be critical for the deployment of Reinforcement Learning (RL) in real-life applications. For example, plane landing and take-off should ideally occur with probability one.
Wang, Ziyan, Sootla, Aivar, Mguni, David, Jafferjee, Taher, Cowen-Rivers, Alexander I, Bou-Ammar, Haitham, Wang, Jun   +6 more
core   +1 more source

Privacy-Preserving Reinforcement Learning Using Homomorphic Encryption in Cloud Computing Infrastructures

IEEE Access, 2020
Reinforcement learning (RL) is a learning technique that enables state-dependent learning through feedback from an environment and makes an action decision for maximizing a reward without prior knowledge of the environment.
Jaehyoung Park, Dong Seong Kim, Hyuk Lim
doaj   +1 more source

Disentangled representations for improved generalisation in deep reinforcement learning [PDF]

Real-world environments are diverse and unpredictable, so Reinforcement Learning (RL) agents need to be robust to environment changes and adapt quickly.
Dunion, Mhairi
core   +1 more source

An Open-Loop Baseline for Reinforcement Learning Locomotion Tasks [PDF]

In search of a simple baseline for Deep Reinforcement Learning in locomotion tasks, we propose a model-free open-loop strategy. By leveraging prior knowledge and the elegance of simple oscillators to generate periodic joint motions, it achieves ...
Raffin, Antonin, Albu-Schäffer, Alin Olimpiu, Silverio, Joao, Stulp, Freek, Kober, Jens, Sigaud, Olivier, Edoardo Zorzi, Plaat, A., Plaat A., Moerland, T.M., Alberto Castellini, Marcello Restelli, Ponse, K., Duilio Cirino, Riccardo Zamboni, Georgios Chalkiadakis, Kleuker, J.F, Mirco Mutti, Leonidas Bakopoulos, Alessandro Farinelli   +19 more
core   +1 more source

Memory-Assisted Reinforcement Learning for Diverse Molecular De Novo Design [PDF]

, 2020
In de novo molecular design, recurrent neural networks (RNN) have been shown to be effective methods for sampling and generating novel chemical structures.
Thomas, Blaschke, Ola, Engkvist, Jürgen, Bajorath, Hongming, Chen   +3 more
core   +1 more source