Learning momentum: integration and experimentation

We further study the effects of learning momentum as defined by Arkin, Clark and Ram (1992) on robots, both simulated and real, attempting to traverse obstacle fields in order to reach a goal. Integration of these results into a large-scale software architecture, MissionLab, provides the ability to exercise these algorithms in novel ways. Insight is also sought in reference to when different learning momentum strategies should be used.

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

[2]  Russell J. Clark,et al.  Learning momentum: online performance enhancement for reactive systems , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[3]  Minoru Asada,et al.  Vision-based reinforcement learning for purposive behavior acquisition , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

[4]  Ronald C. Arkin,et al.  Motor Schema — Based Mobile Robot Navigation , 1989, Int. J. Robotics Res..

[5]  Ronald C. Arkin,et al.  Multiagent Mission Specification and Execution , 1997, Auton. Robots.

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