A5084387194- Reinforcement Learning in Robotics
- Anomaly Detection Techniques and Applications
- Advanced Neural Network Applications
- Robotic Path Planning Algorithms
- Advanced Malware Detection Techniques
- Topic Modeling
- Machine Learning and Data Classification
- Radiomics and Machine Learning in Medical Imaging
- Data Quality and Management
- Adversarial Robustness in Machine Learning
- Natural Language Processing Techniques
- Network Security and Intrusion Detection
- AI in cancer detection
- Imbalanced Data Classification Techniques
- Robot Manipulation and Learning
- Autonomous Vehicle Technology and Safety
Changzhou University
2022-2024
Abstract In order to achieve collision-free path planning in complex environment, Munchausen deep Q-learning network (M-DQN) is applied mobile robot learn the best decision. On basis of Soft-DQN, M-DQN adds scaled log-policy immediate reward. The method allows agent do more exploration. However, algorithm has problem slow convergence. A new and improved (DM-DQN) proposed paper address problem. First, its structure was on by decomposing into a value function an advantage function, thus...
Twin delayed deep deterministic (TD3) policy gradient has several limitations when applied in planning a path environment with number of dilemmas according to our experiment, due the complexity robot task, rate convergence TD3 algorithm is slow and collision high. To address this problem, dense dueling twin (D3-TD3) architecture proposed, method that preserves important information from cross-layer inputs through connections divides network into value function dominance function, thus,...
Abstract In the field of robot path planning, Deep Reinforcement Learning (DRL) has demonstrated considerable potential as a cutting-edge artificial intelligence technology. However, effective utilization representation learning in planning tasks, which is pivotal for successful DRL performance, remained elusive. This challenge arises from predominant use compact vectors derived directly low-level sensors state task. meaningful representations on such states often proves to be challenging....