论文信息 - Machine Learning for Autonomous Robots

Machine Learning for Autonomous Robots

Although Reinforcement Learning methods have meanwhile been successfully applied to a wide range of different application scenarios, there is still a lack of methods that would allow the direct application of reinforcement learning to real systems. The key capability of such learning systems is the efficency with respect to the number of interactions with the real system. Several examples are given that illustrate recent progress made in that direction.

Martin A. Riedmiller

[1] Andrew G. Barto,et al. Improving Elevator Performance Using Reinforcement Learning , 1995, NIPS.

[2] Andrew G. Barto,et al. Learning to Act Using Real-Time Dynamic Programming , 1995, Artif. Intell..

[3] Andrew G. Barto,et al. Reinforcement learning , 1998 .

[4] Sridhar Mahadevan,et al. Optimizing Production Manufacturing Using Reinforcement Learning , 1998, FLAIRS.

[5] Martin A. Riedmiller,et al. Using reinforcement learning for engine control , 1999 .

[6] Martin A. Riedmiller. Concepts and Facilities of a Neural Reinforcement Learning Control Architecture for Technical Process Control , 1999, Neural Computing & Applications.

[7] Martin A. Riedmiller,et al. Reinforcement learning on an omnidirectional mobile robot , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[8] Erkki Oja,et al. Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003 , 2003, Lecture Notes in Computer Science.

[9] Martin A. Riedmiller,et al. Learning to Control at Multiple Time Scales , 2003, ICANN.

[10] Martin A. Riedmiller,et al. Using Machine Learning Techniques in Complex Multi-Agent Domains , 2003 .