http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Implementing Action Mask in Proximal Policy Optimization (PPO) Algorithm
Cheng-Yen Tang,Chien-Hung Liu,Woei-Kae Chen,Shingchern D. You 한국통신학회 2020 ICT Express Vol.6 No.3
The proximal policy optimization (PPO) algorithm is a promising algorithm in reinforcement learning. In this paper, we propose to add an action mask in the PPO algorithm. The mask indicates whether an action is valid or invalid for each state. Simulation results show that, when compared with the original version, the proposed algorithm yields much higher return with a moderate number of training steps. Therefore, it is useful and valuable to incorporate such a mask if applicable.
I-Mei Lin,Sheng-Yu Fan,Cheng-Fang Yen,Yi-Chun Yeh,Tze‐Chun Tang,Mei-Feng Huang,Tai-Ling Liu,Peng-Wei Wang,Huang-Chi Lin,Hsin-Yi Tsai,Yu-Che Tsai 대한정신약물학회 2019 CLINICAL PSYCHOPHARMACOLOGY AND NEUROSCIENCE Vol.17 No.2
Objective: Autonomic imbalance is considered a psychopathological mechanism underlying major depressive disorder (MDD). Heart rate variability (HRV) is an index for autonomic activation. Poor sleep quality is common among patients with MDD. HRV biofeedback (BF) has been used for regulating autonomic balance among patients with physical illness and mental disorders. The purpose of present study was to examine the effects of HRV-BF on depressive symptoms, sleep quality, pre-sleep arousal, and HRV indices, in patients with MDD and insomnia. Methods: In this case-controlled study, patients with MDD and Pittsburgh Sleep Quality Index (PSQI) score higher than 6 were recruited. The HRV-BF group received weekly 60-minute protocol for 6 weeks, and the control group who have matched the age and sex received medical care only. All participants were assessed on Beck Depression Inventory-II, Back Anxiety Inventory, PSQI, and Pre-Sleep Arousal Scale. Breathing rates and electrocardiography were also performed under resting state at pre-testing, and post-testing conditions and for the HRV-BF group, also at 1-month follow-up. Results: In the HRV-BF group, symptoms of depression and anxiety, sleep quality, and pre-sleep arousal were significantly improved, and increased HRV indices, compared with the control group. Moreover, in the HRV-BF group, significantly improved symptoms of depression and anxiety, decreased breathing rates, and increased HRV indices were detected at post-testing and at 1-month follow-up, compared with pre-testing values. Conclusion: This study confirmed that HRV-BF is a useful psychosocial intervention for improving autonomic balance, baroreflex, and symptoms of depression and insomnia in MDD patients.