Papers_L
·
他最大的问题在于，对任务间相似度的假设太强了
发简信
IP属地：安徽
-
论文解读：Universal Successor Features Approximators论文题目：Universal Successor Features Approximators链接：https://arxiv.org/pdf/1812.07626出处：IC...
-
-
深入理解：强化学习之Successor Representation前面写过两篇论文解读，都是关于Successor Features在迁移强化学习中的应用（点击进入第一篇[https://www.jianshu.com/p/3d816106...
-
论文解读：Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Impr...论文题目：Transfer in Deep Reinforcement Learning Using Successor Features and Generalised P...
-
论文解读：Successor Features for Transfer in Reinforcement Learning论文题目：Successor Features for Transfer in Reinforcement Learning 论文链接：http://papers.nips....
-
论文解读：Policy Transfer in Reinforcement Learning: A Selective Exploration Approach论文题目：Policy Transfer in Reinforcement Learning: A Selective Exploration Approach 论文链接： ...
-
论文解读：Policy Distillation and Value Matching in Multiagent Reinforcement Learning论文题目：Policy Distillation and Value Matching in Multiagent Reinforcement Learning 论文链接：h...
