图 书 馆开课单位--克里特理工大学
1 1/1
1Model-Free Reinforcement Learning as Mixture Learning[无模型强化学习作为混合学习]
Nikos Vlassis(克里特理工大学) We cast model-free reinforcement learning as the problem of maximizing the likelihood of a probabilistic mixture model via sampling, addressing both t...
热度：127
Nikos Vlassis(克里特理工大学) We cast model-free reinforcement learning as the problem of maximizing the likelihood of a probabilistic mixture model via sampling, addressing both t...
热度：127
2Binary Action Search for Learning Continuous-Action Control Policies[学习连续动作控制策略的二元动作搜索]
Jason Pazis(克里特理工大学) Reinforcement Learning methods for controlling stochastic processes typically assume a small and discrete action space. While continuous action spaces...
热度：40
Jason Pazis(克里特理工大学) Reinforcement Learning methods for controlling stochastic processes typically assume a small and discrete action space. While continuous action spaces...
热度：40
1 1/1