07 2021 档案

Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
摘要：文章简介 这是一篇关于元强化学习和多任务学习benchmark的文章，发表在PMLR 2020(Proceedings of Machine Learning Research)上。针对于目前元强化学习算法通常只能在简单的benchmark上测试，如在2d navigation的任务中，设置目标点坐 阅读全文
posted @ 2021-07-23 10:45 tianyma的技术博客 阅读(1643) 评论(0) 推荐(0)
元强化学习论文汇总
摘要：Challenges of meta-RL design a set of tasks that are interrelated find the inter-representation fast adaptation to new tasks Papers environment Meta-W 阅读全文
posted @ 2021-07-17 22:42 tianyma的技术博客 阅读(537) 评论(0) 推荐(0)