| Publication |
Sentence |
Publish Date |
Extraction Date |
Species |
| Xiang Zhang, Zhiwei Song, Yiwen Wan. Reinforcement Learning-based Kalman Filter for Adaptive Brain Control in Brain-Machine Interface Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference. vol 2021. 2021-12-11. PMID:34892625. |
on the other hand, reinforcement learning (rl) has the advantage of adaptive updating by the reward signal. |
2021-12-11 |
2023-08-13 |
human |
| Xiang Zhang, Zhiwei Song, Yiwen Wan. Reinforcement Learning-based Kalman Filter for Adaptive Brain Control in Brain-Machine Interface Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference. vol 2021. 2021-12-11. PMID:34892625. |
the rl's parameters are continuously adjusted by the reward signal in bc. |
2021-12-11 |
2023-08-13 |
human |
| Xiang Shen, Xiang Zhang, Yiwen Wan. Kernel Temporal Difference based Reinforcement Learning for Brain Machine Interfaces Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference. vol 2021. 2021-12-11. PMID:34892650. |
current rl decoders deal with tasks with immediate reward delivery. |
2021-12-11 |
2023-08-13 |
Not clear |
| Xiang Shen, Xiang Zhang, Yiwen Wan. Kernel Temporal Difference based Reinforcement Learning for Brain Machine Interfaces Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference. vol 2021. 2021-12-11. PMID:34892650. |
but for tasks where the reward is only given by the end of the trial, existing rl methods may take a long time to train and are prone to becoming trapped in the local minima. |
2021-12-11 |
2023-08-13 |
Not clear |
| Xiang Shen, Xiang Zhang, Yiwen Wan. Kernel Temporal Difference based Reinforcement Learning for Brain Machine Interfaces Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference. vol 2021. 2021-12-11. PMID:34892650. |
we find that introducing the td method to qagkrl achieves a prediction accuracy of 96.2% ± 0.77% (mean ± std), which is significantly better the other two methods.clinical relevance-this paper proposes a novel kernel temporal difference rl method for the multi-step task with delayed reward delivery, which potentially enables bmi online continuous decoding. |
2021-12-11 |
2023-08-13 |
Not clear |
| Chaozheng Wang, Zhenhao Nong, Cuiyun Gao, Zongjie Li, Jichuan Zeng, Zhenchang Xing, Yang Li. Enriching query semantics for code search with reinforcement learning. Neural networks : the official journal of the International Neural Network Society. vol 145. 2021-12-07. PMID:34710788. |
with rl, the code search performance is considered as a reward for producing accurate semantic enriched queries. |
2021-12-07 |
2023-08-13 |
Not clear |
| Angela Langdon, Matthew Botvinick, Hiroyuki Nakahara, Keiji Tanaka, Masayuki Matsumoto, Ryota Kana. Meta-learning, social cognition and consciousness in brains and machines. Neural networks : the official journal of the International Neural Network Society. vol 145. 2021-12-07. PMID:34735893. |
a well-known example is the case of reinforcement learning (rl), which has stimulated neuroscience research on how animals learn to adjust their behavior to maximize reward. |
2021-12-07 |
2023-08-13 |
human |
| Zehong Cao, KaiChiu Wong, Chin-Teng Li. Weak Human Preference Supervision for Deep Reinforcement Learning. IEEE transactions on neural networks and learning systems. vol 32. issue 12. 2021-12-01. PMID:34101604. |
the current reward learning from human preferences could be used to resolve complex reinforcement learning (rl) tasks without access to a reward function by defining a single fixed preference between pairs of trajectory segments. |
2021-12-01 |
2023-08-13 |
human |
| Brosnan Yuen, Minh Tu Hoang, Xiaodai Dong, Tao L. Universal activation function for machine learning. Scientific reports. vol 11. issue 1. 2021-11-30. PMID:34548504. |
for the bipedalwalker-v2 rl dataset, the uaf achieves the 250 reward in [formula: see text] epochs with a brand new activation function, which gives the fastest convergence rate among the activation functions. |
2021-11-30 |
2023-08-13 |
Not clear |
| Ethan Trepka, Mehran Spitmaan, Bilal A Bari, Vincent D Costa, Jeremiah Y Cohen, Alireza Soltan. Entropy-based metrics for predicting choice behavior based on local response to reward. Nature communications. vol 12. issue 1. 2021-11-30. PMID:34772943. |
more recently, many reinforcement learning (rl) models have been developed to explain choice by integrating reward feedback over time. |
2021-11-30 |
2023-08-13 |
mouse |
| Luiza Caetano Garaffa, Maik Basso, Andrea Aparecida Konzen, Edison Pignaton de Freita. Reinforcement Learning for Mobile Robotics Exploration: A Survey. IEEE transactions on neural networks and learning systems. vol PP. 2021-11-17. PMID:34767514. |
this survey summarizes: what are the employed rl algorithms and how they compose the so far proposed mobile robot exploration strategies; how robotic exploration solutions are addressing typical rl problems like the exploration-exploitation dilemma, the curse of dimensionality, reward shaping, and slow learning convergence; and what are the performed experiments and software tools used for learning and testing. |
2021-11-17 |
2023-08-13 |
Not clear |
| He A Xu, Alireza Modirshanechi, Marco P Lehmann, Wulfram Gerstner, Michael H Herzo. Novelty is not surprise: Human exploratory and adaptive behavior in sequential decision-making. PLoS computational biology. vol 17. issue 6. 2021-10-18. PMID:34081705. |
classic reinforcement learning (rl) theories cannot explain human behavior in the absence of external reward or when the environment changes. |
2021-10-18 |
2023-08-13 |
human |
| Yichuan Zhang, Yixing Lan, Qiang Fang, Xin Xu, Junxiang Li, Yujun Zen. Efficient Reinforcement Learning from Demonstration via Bayesian Network-Based Knowledge Extraction. Computational intelligence and neuroscience. vol 2021. 2021-10-05. PMID:34603434. |
experimental results show that the proposed rlbnk method improves the learning efficiency of corresponding baseline rl algorithms under both normal and sparse reward settings. |
2021-10-05 |
2023-08-13 |
human |
| Thomas Nakken Larsen, Halvor Ødegård Teigen, Torkel Laache, Damiano Varagnolo, Adil Rashee. Comparing Deep Reinforcement Learning Algorithms' Ability to Safely Navigate Challenging Waters. Frontiers in robotics and AI. vol 8. 2021-10-01. PMID:34589522. |
compared to the introduced rl algorithms, the results show that the proximal policy optimization (ppo) algorithm exhibits superior robustness to changes in the environment complexity, the reward function, and when generalized to environments with a considerable domain gap from the training environment. |
2021-10-01 |
2023-08-13 |
Not clear |
| Katharine Nowakowski, Philippe Carvalho, Jean-Baptiste Six, Yann Maillet, Anh Tu Nguyen, Ismail Seghiri, Loick M'Pemba, Theo Marcille, Sy Toan Ngo, Tien-Tuan Da. Human locomotion with reinforcement learning using bioinspired reward reshaping strategies. Medical & biological engineering & computing. vol 59. issue 1. 2021-09-29. PMID:33417125. |
consequently, the objective of the present work was to design and evaluate specific bioinspired reward function strategies for human locomotion learning within an rl framework. |
2021-09-29 |
2023-08-13 |
human |
| Junyang Chen, Zhiguo Gong, Wei Wang, Weiwen Liu, Ming Yang, Cong Wan. TAM: Targeted Analysis Model With Reinforcement Learning on Short Texts. IEEE transactions on neural networks and learning systems. vol 32. issue 6. 2021-09-28. PMID:32726283. |
in this work, we design a reward function of rl to prevent the false propagation problem induced by gibbs sampling during the clustering. |
2021-09-28 |
2023-08-13 |
Not clear |
| Matthew Chalk, Gasper Tkacik, Olivier Marr. Inferring the function performed by a recurrent neural network. PloS one. vol 16. issue 4. 2021-09-15. PMID:33857170. |
we then show how one can use inverse rl to infer the reward function optimised by the network from observing its responses. |
2021-09-15 |
2023-08-13 |
Not clear |
| Ying Liu, Nidan Qiao, Yuksel Altine. Reinforcement Learning in Neurocritical and Neurosurgical Care: Principles and Possible Applications. Computational and mathematical methods in medicine. vol 2021. 2021-09-10. PMID:33680069. |
this review is aimed at introducing rl's basic concepts, including three basic components: the state, the action, and the reward. |
2021-09-10 |
2023-08-13 |
Not clear |
| Hangkai Hu, Gao Huang, Xiang Li, Shiji Son. Meta-Reinforcement Learning With Dynamic Adaptiveness Distillation. IEEE transactions on neural networks and learning systems. vol PP. 2021-08-31. PMID:34464267. |
in our experiments, our method achieves 10%-20% higher asymptotic reward than probabilistic embeddings for actor-critic rl (pearl). |
2021-08-31 |
2023-08-13 |
Not clear |
| Irene van de Vijver, Romain Ligneu. Relevance of working memory for reinforcement learning in older adults varies with timescale of learning. Neuropsychology, development, and cognition. Section B, Aging, neuropsychology and cognition. vol 27. issue 5. 2021-08-24. PMID:31544587. |
age-related rl changes, however, are mostly attributed to decreased reward prediction-error (rpe) signaling. |
2021-08-24 |
2023-08-13 |
Not clear |