2026/8/24 8:37:38
DI-drive DREX 偏好逆强化学习教程:按噪声等级自动给示范数据排序,学会比专家更好的奖励模型
DI-drive DREX 偏好逆强化学习教程:按噪声等级自动给示范数据排序,学会比专家更好的奖励模型 【免费下载链接】DI-drive Decision Intelligence Platform for Autonomous Driving simulation. 项目地址: https://gitcode.com/gh_mirrors/di/DI-drive …