首页|Studies in the Area of Robotics Reported from Symbiosis International (Deemed Un iversity) [Mobile robot path planning using deep deterministi c policy gradient with differential gaming (DDPG-DG) exploration]
Studies in the Area of Robotics Reported from Symbiosis International (Deemed Un iversity) [Mobile robot path planning using deep deterministi c policy gradient with differential gaming (DDPG-DG) exploration]
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
2024 OCT 09 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Investigators publish new report on robotics. Acc ording to news reporting from Pune, India, by NewsRx journalists, research state d, "Mobile robot path planning involves decision-making in uncertain, dynamic co nditions, where Reinforcement Learning (RL) algorithms excel in generating safe and optimal paths. The Deep Deterministic Policy Gradient (DDPG) is an RL techni que focused on mobile robot navigation." The news editors obtained a quote from the research from Symbiosis International (Deemed University): "RL algorithms must balance exploitation and exploration t o enable effective learning. The balance between these actions directly impacts learning efficiency. This research proposes a method combining the DDPG strategy for exploitation with the Differential Gaming (DG) strategy for exploration. Th e DG algorithm ensures the mobile robot always reaches its target without collis ions, thereby adding positive learning episodes to the memory buffer. An epsilon -greedy strategy determines whether to explore or exploit. When exploration is c hosen, the DG algorithm is employed. The combination of DG strategy with DDPG fa cilitates faster learning by increasing the number of successful episodes and re ducing the number of failure episodes in the experience buffer. The DDPG algorit hm supports continuous state and action spaces, resulting in smoother, non-jerky movements and improved control over the turns when navigating obstacles. Reward shaping considers finer details, ensuring even small advantages in each iterati on contribute to learning."
Symbiosis International (Deemed Universi ty)PuneIndiaAsiaAlgorithmsEmerging TechnologiesMachine LearningRob otRobotics
NETL
NSTL
