Advanced Search Results For "REINFORCEMENT learning"
Your filters
Predictive hierarchical reinforcement learning for path-efficient mapless navigation with moving target.
Publication Type: Academic Journal
Source(s): Neural networks : the official journal of the International Neural Network Society [Neural Netw] 2023 Aug; Vol. 165, pp. 677-688. Date of Electronic Publication: 2023 Jun 10.
Abstract: Deep reinforcement learning (DRL) has been proven as a powerful approach for robot navigation over the past few years. DRL-based navigation does not require the pre-construction of a map, instead, high-performance navigation skills can be learned from ...
Dynamic organization of cerebellar climbing fiber response and synchrony in multiple functional components reduces dimensions for reinforcement learning.
Publication Type: Academic Journal
Source(s): ELife [Elife] 2023 Sep 15; Vol. 12. Date of Electronic Publication: 2023 Sep 15.
Abstract: Cerebellar climbing fibers convey diverse signals, but how they are organized in the compartmental structure of the cerebellar cortex during learning remains largely unclear. We analyzed a large amount of coordinate-localized two-photon imaging data fr...
Discrete-time robust event-triggered actuator fault-tolerant control based on adaptive networks and reinforcement learning.
Publication Type: Academic Journal
Source(s): Neural networks : the official journal of the International Neural Network Society [Neural Netw] 2023 Sep; Vol. 166, pp. 541-554. Date of Electronic Publication: 2023 Aug 09.
Abstract: This paper focuses on the topic of fault-tolerant control for discrete-time systems with nonlinear uncertainties and actuator faults. It considers both passive and active faults as part of the analysis and design. The proposed adaptive controller, base...
Social Concepts Simplify Complex Reinforcement Learning.
Publication Type: Academic Journal
Source(s): Psychological science [Psychol Sci] 2023 Sep; Vol. 34 (9), pp. 968-983. Date of Electronic Publication: 2023 Jul 20.
Abstract: Humans often generalize rewarding experiences across abstract social roles. Theories of reward learning suggest that people generalize through model-based learning, but such learning is cognitively costly. Why do people seem to generalize across social...
Confirmatory reinforcement learning changes with age during adolescence.
Publication Type: Academic Journal
Source(s): Developmental science [Dev Sci] 2023 May; Vol. 26 (3), pp. e13330. Date of Electronic Publication: 2022 Oct 27.
Abstract: Understanding how learning changes during human development has been one of the long-standing objectives of developmental science. Recently, advances in computational biology have demonstrated that humans display a bias when learning to navigate novel ...
Having multiple selves helps learning agents explore and adapt in complex changing worlds.
Publication Type: Academic Journal
Source(s): Proceedings of the National Academy of Sciences of the United States of America [Proc Natl Acad Sci U S A] 2023 Jul 11; Vol. 120 (28), pp. e2221180120. Date of Electronic Publication: 2023 Jul 03.
Abstract: Satisfying a variety of conflicting needs in a changing environment is a fundamental challenge for any adaptive agent. Here, we show that designing an agent in a modular fashion as a collection of subagents, each dedicated to a separate need, powerfull...
Credit assignment with predictive contribution measurement in multi-agent reinforcement learning.
Publication Type: Academic Journal
Source(s): Neural networks : the official journal of the International Neural Network Society [Neural Netw] 2023 Jul; Vol. 164, pp. 681-690. Date of Electronic Publication: 2023 May 20.
Abstract: Credit assignment is a crucial issue in multi-agent tasks employing a centralized training and decentralized execution paradigm. While value decomposition has demonstrated strong performance in Q-learning-based approaches and certain Actor-Critic varia...
The NK1 antagonist L-733,060 facilitates sequence learning.
Publication Type: Academic Journal
Source(s): Journal of psychopharmacology (Oxford, England) [J Psychopharmacol] 2023 Jun; Vol. 37 (6), pp. 610-626. Date of Electronic Publication: 2023 Mar 29.
Abstract: Background: Although several brain regions and electrophysiological patterns have been related to sequence learning, less attention has been paid to the role that different neuromodulators play.Aims: Here we sought to investigate the role of substance ...
Hierarchical Attention Master-Slave for heterogeneous multi-agent reinforcement learning.
Publication Type: Academic Journal
Source(s): Neural networks : the official journal of the International Neural Network Society [Neural Netw] 2023 May; Vol. 162, pp. 359-368. Date of Electronic Publication: 2023 Mar 04.
Abstract: Most multi-agent reinforcement learning (MARL) approaches optimize strategy by improving itself, while ignoring the limitations of homogeneous agents that may have single function. However, in reality, the complex tasks tend to coordinate various types...
Distributional generative adversarial imitation learning with reproducing kernel generalization.
Publication Type: Academic Journal
Source(s): Neural networks : the official journal of the International Neural Network Society [Neural Netw] 2023 Aug; Vol. 165, pp. 43-59. Date of Electronic Publication: 2023 May 25.
Abstract: Generative adversarial imitation learning (GAIL) regards imitation learning (IL) as a distribution matching problem between the state-action distributions of the expert policy and the learned policy. In this paper, we focus on the generalization and co...