An Approach to Subjective Computing: a Robot that Learns from Interaction with Humans
An Approach to Subjective Computing: a Robot that Learns from Interaction with Humans
复制标题
主观计算方法：从与人类交互中学习的机器人
DOI：
10.1109/tamd.2013.2271739
复制
发表时间：
2014
影响因子：
--
通讯作者：
K.
中科院分区：
文献类型：
--
作者：
Gruneberg;P. and Suzuki;K.
我们提出了一种主观计算方法，用于设计在主观智能方面表现出更强适应性和更灵活行为的未来机器人。我们没有将主体性封装到高阶状态中，而是通过关系方法展示了主观智能如何通过自主自我参照和直接世界耦合的相互作用来实现。主体性涉及主体认知空间的关系安排。这个理论概念被缩小为通过二元反馈来训练一个强化学习代理的问题。提出了实现主观计算的算法。通过对人类感知机器人行为的问卷调查，进一步证实了主体性的关系特征。结果表明，主观智力是无法从外部观察到的。总之，我们得出结论，主观智能在关系方面是完全可处理的，因此在人工代理中是可实现的。
We present an approach to subjective computing for the design of future robots that exhibit more adaptive and flexible behavior in terms of subjective intelligence. Instead of encapsulating subjectivity into higher order states, we show by means of a relational approach how subjective intelligence can be implemented in terms of the reciprocity of autonomous self-referentiality and direct world-coupling. Subjectivity concerns the relational arrangement of an agent's cognitive space. This theoretical concept is narrowed down to the problem of coaching a reinforcement learning agent by means of binary feedback. Algorithms are presented that implement subjective computing. The relational characteristic of subjectivity is further confirmed by a questionnaire on human perception of the robot's behavior. The results imply that subjective intelligence cannot be externally observed. In sum, we conclude that subjective intelligence in relational terms is fully tractable and therefore implementable in artificial agents.