A5000386701- Virtual Reality Applications and Impacts
- Educational Games and Gamification
- Intelligent Tutoring Systems and Adaptive Learning
- Reinforcement Learning in Robotics
- RNA Research and Splicing
- Human-Automation Interaction and Safety
- Human Pose and Action Recognition
- Social Robot Interaction and HRI
- Online Learning and Analytics
- Multi-Agent Systems and Negotiation
- Robotic Path Planning Algorithms
- RNA modifications and cancer
- 3D Shape Modeling and Analysis
- Adaptive Dynamic Programming Control
- Visual and Cognitive Learning Processes
- Human Motion and Animation
- Teleoperation and Haptic Systems
- Augmented Reality Applications
- Cancer-related molecular mechanisms research
University of California, Merced
2019-2023
Mudanjiang Medical University
2018
Abstract As a component of p53-dependent lncRNA (long non-coding RNA), PANDAR (the promoter CDKN1A antisense DNA damage activated RNA) participates in the epigenetic regulation human cancer. However, involvement cancer chemoresistance is unknown. In this study, we report that serves as negative regulator cisplatin sensitivity ovarian via -SRFS2-p53 feedback nuclear. Our data showed among drugs commonly used therapy, induces higher levels compared with doxorubicin and paclitaxel. We also...
We present a deep learning method for composite and task-driven motion control physically simulated characters. In contrast to existing data-driven approaches using reinforcement that imitate full-body motions, we learn decoupled motions specific body parts from multiple reference simultaneously directly by leveraging the use of discriminators in GAN-like setup. this process, there is no need any manual work produce learning. Instead, policy explores itself how can be combined automatically....
In this paper we investigate interaction strategies for autonomous virtual trainers. Fourteen participants were immersed in our VR system to learn relative areas of countries by sorting cubes. We evaluated two different feedback used the trainer assisting participants. One provided Correctness Feedback at end each task, while other Suggestive during task. was most effective given that it received higher preference and led shorter task completion time with equivalent performance outcomes.
Abstract In order to be successfully executed, collaborative tasks performed by two agents often require a cooperative strategy learned. this work, we propose constraint‐based multi‐agent reinforcement learning approach called constrained soft actor critic (C‐MSAC) train control policies for simulated performing multi‐phase tasks. Given task with phases, the first phases are treated as constraints final phase objective, which is addressed centralized training and decentralized execution...
In order to be successfully executed, collaborative tasks performed by two agents often require a cooperative strategy learned. this work, we propose constraint-based multi-agent reinforcement learning approach called Constrained Multi-agent Soft Actor Critic (C-MSAC) train control policies for simulated performing multi-phase tasks. Given task with n phases, the first -1 phases are treated as constraints final phase objective, which is addressed centralized training and decentralized...
In this paper we address feedback strategies for an autonomous virtual trainer. First, a pilot study was conducted to identify and specify assisting participants in performing given task. The task involved sorting cubes according areas of countries displayed on them. Two were specified. first provides correctness by fully correcting user responses at each stage the task, second suggestive only notifying if how response can be corrected. Both implemented training system empirically evaluated....