| Publication |
Sentence |
Publish Date |
Extraction Date |
Species |
| Antoine Théberge, Christian Desrosiers, Arnaud Boré, Maxime Descoteaux, Pierre-Marc Jodoi. What matters in reinforcement learning for tractography. Medical image analysis. vol 93. 2024-01-14. PMID:38219499. |
in this work, we thoroughly explore the different components of the proposed framework, such as the choice of the rl algorithm, seeding strategy, the input signal and reward function, and shed light on their impact. |
2024-01-14 |
2024-01-17 |
Not clear |
| Antoine Théberge, Christian Desrosiers, Arnaud Boré, Maxime Descoteaux, Pierre-Marc Jodoi. What matters in reinforcement learning for tractography. Medical image analysis. vol 93. 2024-01-14. PMID:38219499. |
as such, we ultimately propose a series of recommendations concerning the choice of rl algorithm, the input to the agents, the reward function and more to help future work using reinforcement learning for tractography. |
2024-01-14 |
2024-01-17 |
Not clear |
| Qiming Zou, Einoshin Suzuk. Compact Goal Representation Learning via Information Bottleneck in Goal-Conditioned Reinforcement Learning. IEEE transactions on neural networks and learning systems. vol PP. 2024-01-09. PMID:38190683. |
goal-conditioned rl learns a policy from reward signals to predict actions for reaching desired goals. |
2024-01-09 |
2024-01-10 |
Not clear |
| Qiming Zou, Einoshin Suzuk. Compact Goal Representation Learning via Information Bottleneck in Goal-Conditioned Reinforcement Learning. IEEE transactions on neural networks and learning systems. vol PP. 2024-01-09. PMID:38190683. |
however, in goal-conditioned rl, it is difficult to balance the tradeoff between task-relevant information and task-irrelevant information because of the sparse and delayed learning signals, i.e., reward signals, and the inevitable task-relevant information sacrifice caused by information compression. |
2024-01-09 |
2024-01-10 |
Not clear |
| Yang Lin, Liang Chu, Jincheng Hu, Zhuoran Hou, Jihao Li, Jingjing Jiang, Yuanjian Zhan. Progress and summary of reinforcement learning on energy management of MPS-EV. Heliyon. vol 10. issue 1. 2024-01-01. PMID:38163106. |
this paper first summarizes the previous applications of rl in ems from five aspects: algorithm, perception scheme, decision scheme, reward function, and innovative training method. |
2024-01-01 |
2024-01-05 |
Not clear |
| Elizabeth A Bauer, Brandon K Watanabe, Annmarie MacNamar. Reinforcement learning and the reward positivity with aversive outcomes. Psychophysiology. 2023-11-23. PMID:37994210. |
the reinforcement learning (rl) theory of the reward positivity (rewp), an event-related potential (erp) component that measures reward responsivity, suggests that the rewp should be largest when positive outcomes are unexpected and has been supported by work using appetitive outcomes (e.g., money). |
2023-11-23 |
2023-11-29 |
human |
| Elizabeth A Bauer, Brandon K Watanabe, Annmarie MacNamar. Reinforcement learning and the reward positivity with aversive outcomes. Psychophysiology. 2023-11-23. PMID:37994210. |
here, we tested the predictions of the rl theory by manipulating expectancy in an active/choice-based threat-of-shock doors task that was previously found to elicit the rewp as a reward signal. |
2023-11-23 |
2023-11-29 |
human |
| Elizabeth A Bauer, Brandon K Watanabe, Annmarie MacNamar. Reinforcement learning and the reward positivity with aversive outcomes. Psychophysiology. 2023-11-23. PMID:37994210. |
therefore, the rewp appears to reflect the additive (not interactive) effects of reward and expectancy, challenging the rl theory of the rewp, at least when reward is defined as the absence of an aversive outcome. |
2023-11-23 |
2023-11-29 |
human |
| Mythra V Balakuntala, Glebys T Gonzalez, Juan P Wachs, Richard M Voyle. ASAP-CORPS: A Semi-Autonomous Platform for COntact-Rich Precision Surgery. Military medicine. vol 188. issue Supplement_6. 2023-11-10. PMID:37948233. |
this article presents a method for learning from demonstration, combining knowledge from demonstrations to eliminate reward shaping in reinforcement learning (rl). |
2023-11-10 |
2023-11-20 |
human |
| Jingda Wu, Yanxin Zhou, Haohan Yang, Zhiyu Huang, Chen L. Human-Guided Reinforcement Learning With Sim-to-Real Transfer for Autonomous Navigation. IEEE transactions on pattern analysis and machine intelligence. vol PP. 2023-09-13. PMID:37703148. |
meanwhile, the training of rl on navigation tasks is difficult, which requires a carefully-designed reward function and a large number of interactions, yet rl navigation can still fail due to many corner cases. |
2023-09-13 |
2023-10-07 |
human |
| Jingda Wu, Yanxin Zhou, Haohan Yang, Zhiyu Huang, Chen L. Human-Guided Reinforcement Learning With Sim-to-Real Transfer for Autonomous Navigation. IEEE transactions on pattern analysis and machine intelligence. vol PP. 2023-09-13. PMID:37703148. |
an innovative human-guided rl algorithm is proposed that utilizes a series of mechanisms to improve the effectiveness of human guidance, including human-guided learning objective, prioritized human experience replay, and human intervention-based reward shaping. |
2023-09-13 |
2023-10-07 |
human |
| Maria Cecilia Serafini, Nicolas Rosales, Fabricio Garell. Auto adaptation of closed-loop insulin delivery system using continuous reward functions and incremental discretization. Computer methods in biomechanics and biomedical engineering. 2023-08-07. PMID:37545465. |
in this work, the performance of two reinforcement learning (rl) agents trained under both piecewise and continuous reward functions is evaluated |
2023-08-07 |
2023-08-14 |
Not clear |
| Hongliang Zeng, Ping Zhang, Fang Li, Chubin Lin, Junkang Zho. AHEGC: Adaptive Hindsight Experience Replay With Goal-Amended Curiosity Module for Robot Control. IEEE transactions on neural networks and learning systems. vol PP. 2023-08-01. PMID:37527323. |
with shaped reward functions, reinforcement learning (rl) has recently been successfully applied to several robot control tasks. |
2023-08-01 |
2023-08-14 |
Not clear |
| Hongliang Zeng, Ping Zhang, Fang Li, Chubin Lin, Junkang Zho. AHEGC: Adaptive Hindsight Experience Replay With Goal-Amended Curiosity Module for Robot Control. IEEE transactions on neural networks and learning systems. vol PP. 2023-08-01. PMID:37527323. |
still, if rl can train an agent to complete a task in a sparse reward environment, it is an effective way to address the difficulty of reward function design, but it is still a significant challenge. |
2023-08-01 |
2023-08-14 |
Not clear |
| Gaia Molinaro, Anne G E Collin. Intrinsic rewards explain context-sensitive valuation in reinforcement learning. PLoS biology. vol 21. issue 7. 2023-07-17. PMID:37459394. |
by integrating internally generated signals of reward, standard rl theories should better account for human behavior, including context-sensitive valuation and beyond. |
2023-07-17 |
2023-08-14 |
human |
| Erik M Elster, Ruth Pauli, Sarah Baumann, Stephane A De Brito, Graeme Fairchild, Christine M Freitag, Kerstin Konrad, Veit Roessner, Inti A Brazil, Patricia L Lockwood, Gregor Kohl. Impaired Punishment Learning in Conduct Disorder. Journal of the American Academy of Child and Adolescent Psychiatry. 2023-07-06. PMID:37414274. |
specifically, we tested two competing hypotheses that rl deficits in cd reflect either reward dominance (also known as reward hypersensitivity) or punishment insensitivity (also known as punishment hyposensitivity). |
2023-07-06 |
2023-08-14 |
Not clear |
| Tianhao Liu, Chunhua Yang, Can Zhou, Yonggang Li, Bei Su. Integrated Optimal Control for Electrolyte Temperature With Temporal Causal Network and Reinforcement Learning. IEEE transactions on neural networks and learning systems. vol PP. 2023-06-08. PMID:37289608. |
then, an rl controller is established under each working condition, and the optimal electrolyte temperature is placed into the controller's reward function to assist in control strategy learning. |
2023-06-08 |
2023-08-14 |
Not clear |
| Kibok Nam, Dahye Lee, Seungwan Le. A denoising model based on multi-agent reinforcement learning with data transformation for digital tomosynthesis. Physics in medicine and biology. 2023-05-16. PMID:37192630. |
reinforcement learning (rl) can provide the optimal pollicy, which maximizes a reward, with a small amount of training data for implementing a task. |
2023-05-16 |
2023-08-14 |
Not clear |
| Kibok Nam, Dahye Lee, Seungwan Le. A denoising model based on multi-agent reinforcement learning with data transformation for digital tomosynthesis. Physics in medicine and biology. 2023-05-16. PMID:37192630. |
in this study, we presented a denoising model based on the multi-agent rl for dt imaging in order to improve the performance of the machine learning-based denoising model.
approach: the proposed multi-agent rl network consisted of shared sub-network, value sub-network with a reward map convolution (rmc) technique and policy sub-network with a convolutional gated recurrent unit (convgru). |
2023-05-16 |
2023-08-14 |
Not clear |
| Jesse P Geerts, Samuel J Gershman, Neil Burgess, Kimberly L Stachenfel. A probabilistic successor representation for context-dependent learning. Psychological review. 2023-05-11. PMID:37166847. |
reinforcement learning (rl) provides a framework for learning, by predicting total future reward directly (model-free rl), or via predictions of future states (model-based rl). |
2023-05-11 |
2023-08-14 |
Not clear |