图 书 馆
游戏树中连贯推理的最佳玩法Coherent inference on optimal play in game trees |
|
| 课程网址: | http://videolectures.net/aistats2010_henning_cioop/ |
| 主讲教师: | Philipp Hennig |
| 开课单位: | 马克斯普朗克研究所 |
| 开课时间: | 2010-06-03 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Round-based games are an instance of discrete planning problems. Some of the best contemporary game tree search algorithms use random roll-outs as data. Relying on a good policy, they learn on-policy values by propagating information upwards in the tree, but not between sibling nodes. Here, we present a generative model and a corresponding approximate message passing scheme for inference on the optimal, off-policy value of nodes in smooth AND/OR trees, given random roll-outs. The crucial insight is that the distribution of values in game trees is not completely arbitrary. We define a generative model of the on-policy values using a latent score for each state, representing the value under the random roll-out policy. Inference on the values under the optimal policy separates into an inductive, pre-data step and a deductive, post-data part. Both can be solved approximately with Expectation Propagation, allowing off-policy value inference for any node in the (exponentially big) tree in linear time. |
| 关 键 词: | 游戏; 推理; 离散规划 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-07-29：yumf |
| 阅读次数: | 47 |