发明名称 |
METHODS AND APPARATUS FOR REINFORCEMENT LEARNING |
摘要 |
We describe a method of reinforcement learning for a subject system having multiple states and actions to move from one state to the next. Training data is generated by operating on the system with a succession of actions and used to train a second neural network. Target values for training the second neural network are derived from a first neural network which is generated by copying weights of the second neural network at intervals. |
申请公布号 |
EP3055813(A1) |
申请公布日期 |
2016.08.17 |
申请号 |
EP20140819108 |
申请日期 |
2014.10.07 |
申请人 |
GOOGLE INC. |
发明人 |
MNIH, VOLODYMYR;KAVUKCUOGLU, KORAY |
分类号 |
G06N3/04;G06N99/00 |
主分类号 |
G06N3/04 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|