Autonomous reconstruction of state space for learning of robot behavior

IEEE International Conference on Intelligent Robots and Systems

Volumn 2, Issue , 2000, Pages 891-896

  Yairi, T ^a   Hori, K ^a   Nakasuka, S ^a  

^a UNIVERSITY OF TOKYO   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; COLLISION AVOIDANCE; INTELLIGENT ROBOTS; MOTION PLANNING; POSITION CONTROL; PROXIMITY SENSORS; SENSOR DATA FUSION; STATE SPACE METHODS;

ROBOT BEHAVIOR; STATE SPACE RECONSTRUCTION METHOD;

ROBOT LEARNING;

EID: 0034446219     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. Multiresolutional intelligent controller for baby robot
2. Action-based sensor space categorization for robot learning
3. Input generalization in delayed reinforcement learning: An algorithm and performance comparisons
4. The partigame algorithm for variable resolution reinforcement learning in multidimensional state-spaces
5. Learning efficient classification procedures and their application to chess end games
6. Reasonable performance in less learning time by real robot based on incremental state space segmentation
7. Simultaneous learning of situation classification based on rewards and behavior selection based on the situation
8. State abstraction from heterogeneous and redundant sensor information