The necessity of average rewards in cooperative multirobot learning

Proceedings - IEEE International Conference on Robotics and Automation

Volumn 2, Issue , 2002, Pages 1296-1301

  Tangamchit, Poj ^a   Dolan, John M ^a   Khosla, Pradeep K ^a  

^a CARNEGIE MELLON UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DECENTRALIZED CONTROL; DYNAMICS; LEARNING ALGORITHMS; MONTE CARLO METHODS; OPTIMAL CONTROL SYSTEMS;

COOPERATIVE MULTIROBOT LEARNING; MONTE CARLO ALGORITHM; TASK LEVEL MULTIROBOT SYSTEMS;

ROBOT LEARNING;

EID: 0036057598     PISSN: 10504729     EISSN: None     Source Type: Journal    
DOI: 10.1109/ROBOT.2002.1014721     Document Type: Article

References (11)

1. Interaction and intelligent behavior
2. Heterogeneous multi-robot cooperation
3. Dynamic task selection: A simple structure for multirobot systems
4. Reinforcement learning: An introduction
5. Learning from delayed rewards
6. Behavioral diversity in learning robot teams
7. A taxonomy for multi-agent robotics
8. Taxonomies of multirobot task and reward
9. Reinforcement learning: A survey
10. A reinforcement learning for maximizing undiscounted rewards
11. Introduction to robotics