Autonomous development of goals: From generic rewards to goal and self detection
説明
Goals are abstractions that express agents’ intention and allow them to organize their behavior appropriately. How can agents develop such goals autonomously? This paper proposes a conceptual and computational account to this longstanding problem. We argue to consider goals as abstractions of lowerlevel intention mechanisms such as rewards and values, and point out that goals need to be considered alongside with a detection of the own actions’ effects. Then, both goals and self-detection can be learned from generic rewards. We show experimentally that task-unspecific rewards induced by visual saliency lead to self and goal representations that constitute goal-directed reaching.
収録刊行物
-
- 4th International Conference on Development and Learning and on Epigenetic Robotics
-
4th International Conference on Development and Learning and on Epigenetic Robotics 187-194, 2014-10-01
IEEE
