Reinforcement Learning in the Multi-Robot Domain

This paper describes a formulation of reinforcement learning that enables learning in noisy, dynamic environments such as in the complex concurrent multi-robot learning domain. The methodology involves minimizing the learning space through the use of behaviors and conditions, and dealing with the credit assignment problem through shaped reinforcement in the form of heterogeneous reinforcement functions and progress estimators. We experimentally validate the approach on a group of four mobile robots learning a foraging task.

[1]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[2]  David J. Reinkensmeyer,et al.  Model-based robot learning , 1988 .

[3]  Christopher G. Atkeson,et al.  Using Local Models to Control Movement , 1989, NIPS.

[4]  Rodney A. Brooks,et al.  Learning to Coordinate Behaviors , 1990, AAAI.

[5]  Rodney A. Brooks,et al.  The Behavior Language: User''s Guide , 1990 .

[6]  Sridhar Mahadevan,et al.  Scaling Reinforcement Learning to Robotics by Exploiting the Subsumption Architecture , 1991, ML.

[7]  Long Ji Lin,et al.  Programming Robots Using Reinforcement Learning and Teaching , 1991, AAAI.

[8]  Andrew W. Moore,et al.  Fast, Robust Adaptive Control by Learning only Forward Models , 1991, NIPS.

[9]  Rodney A. Brooks,et al.  Intelligence Without Reason , 1991, IJCAI.

[10]  Long-Ji Lin,et al.  Self-improving reactive agents: case studies of reinforcement learning frameworks , 1991 .

[11]  Maja J. Matarić,et al.  Behavior-Based Systems: Key Properties and Implications , 1992 .

[12]  Sridhar Mahadevan,et al.  Automatic Programming of Behavior-Based Robots Using Reinforcement Learning , 1991, Artif. Intell..

[13]  Leslie Pack Kaelbling,et al.  Learning in embedded systems , 1993 .

[14]  Jonas Karlsson,et al.  Learning Multiple Goal Behavior via Task Decomposition and Dynamic Policy Merging , 1993 .

[15]  Maja J. Matarić,et al.  Designing emergent behaviors: from local interactions to collective intelligence , 1993 .

[16]  Sebastian Thrun,et al.  Integrating Inductive Neural Network Learning and Explanation-Based Learning , 1993, IJCAI.

[17]  Dean A. Pomerleau,et al.  Neural Network Perception for Mobile Robot Guidance , 1993 .

[18]  Maja J. Matarić,et al.  Kin Recognition, Similarity, and Group Behavior , 1993 .

[19]  José del R. Millán,et al.  Learning efficient reactive behavioral sequences from basic reflexes in a goal-directed autonomous robot , 1994 .

[20]  Maja J. Matarić,et al.  Leaning to behave socially , 1994 .

[21]  S. Schaal,et al.  Robot juggling: implementation of memory-based learning , 1994, IEEE Control Systems.

[22]  Maja J. Mataric,et al.  Interaction and intelligent behavior , 1994 .

[23]  Lynne E. Parker,et al.  Heterogeneous multi-robot cooperation , 1994 .

[24]  M. Matarić.  Learning to Behave Socially , 1994 .

[25]  Minoru Asada,et al.  Coordination of multiple behaviors acquired by a vision-based reinforcement learning , 1994, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94).

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

[27]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.