“大数据智能-课程阅读3”版本间的差异
来自iCenter Wiki
(以“[http://rll.berkeley.edu/deeprlworkshop/ Deep Reinforcement Learning Workshop, NIPS 2015] [https://sites.google.com/site/deeprlnips2016/ Deep Reinforcement Learning...”为内容创建页面) |
2015011315(讨论 | 贡献) |
||
第4行: | 第4行: | ||
− | 第一组 Learning | + | 第一组 Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter? |
第二组 Off-Policy Neural Fitted Actor-Critic | 第二组 Off-Policy Neural Fitted Actor-Critic |
2016年12月19日 (一) 17:10的版本
Deep Reinforcement Learning Workshop, NIPS 2015
Deep Reinforcement Learning Workshop, NIPS 2016
第一组 Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?
第二组 Off-Policy Neural Fitted Actor-Critic
第三组 A Deep Hierarchical Approach to Lifelong Learning in Minecraft
第五组 Guided Deep Reinforcement Learning for Additive Manufacturing Control Application
第六组 Deep Visual Foresight for Planning Robot Motion