arXiv 1702.055732017-02-18cs.CV

联合目标搜索的协同深度强化学习

Collaborative Deep Reinforcement Learning for Joint Object Search

Peking University（北京大学）；Microsoft Research（微软研究院）

Xiangyu Kong, Bo Xin, Yizhou Wang, Gang Hua

摘要：

我们研究的问题，联合自顶向下主动搜索的多个对象的互动，例如，骑自行车的人，桌子上的杯子等。这样的对象在交互下通常可以向彼此提供上下文线索以促进更有效的搜索。通过将每个检测器视为代理，我们提出了第一个协作多代理深度强化学习算法来学习联合主动对象定位的最佳策略，该算法有效地利用了这种有益的上下文信息。我们通过Q网络之间的门交叉连接来学习智能体通信，这是由一种新的多智能体深度Q-学习算法与联合开发采样促进的。我们在多个目标检测基准上验证了我们提出的方法。我们的模型不仅有助于提高最先进的主动定位模型的性能，还揭示了直观可解释的有趣的协同检测模式。

英文摘要：

We examine the problem of joint top-down active search of multiple objects under interaction, e.g., person riding a bicycle, cups held by the table, etc.. Such objects under interaction often can provide contextual cues to each other to facilitate more efficient search. By treating each detector as an agent, we present the first collaborative multi-agent deep reinforcement learning algorithm to learn the optimal policy for joint active object localization, which effectively exploits such beneficial contextual information. We learn inter-agent communication through cross connections with gates between the Q-networks, which is facilitated by a novel multi-agent deep Q-learning algorithm with joint exploitation sampling. We verify our proposed method on multiple object detection benchmarks. Not only does our model help to improve the performance of state-of-the-art active localization models, it also reveals interesting co-detection patterns that are intuitively interpretable.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

摘要：

英文摘要：

相关论文