Continuous-action Q-learning

Machine Learning

Volumn 49, Issue 2-3, 2002, Pages 247-265

  Millán, José Del R ^a   Posenato, Daniele ^a   Dedieu, Eric ^a  

^a JOINT RESEARCH CENTRE   (Italy)

Author keywords

Continuous domains; Incremental topology preserving maps; Real time operation; Reinforcement learning

Indexed keywords

AUTONOMOUS AGENTS; ESTIMATION; OPTIMIZATION; REAL TIME SYSTEMS; TOPOLOGY;

INCREMENTAL TOPOLOGY PRESERVING MAPS; Q LEARNING; REINFORCEMENT LEARNING; TEMPORAL DIFFERENCE METHODS;

LEARNING ALGORITHMS;

EID: 0036832960     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1017988514716     Document Type: Article

References (23)

1. Residual algorithms: Reinforcement learning with function approximation
2. Neuronlike elements that can solve difficult learning control problems
3. Efficient occupancy grids for variable resolution map building
4. A growing neural gas network learns topologies
5. Self-improving reactive agents based on reinforcement learning, planning and teaching
6. Average reward reinforcement learning: Foundations, algorithms, and empirical results
7. Learning reaching strategies through reinforcement for a sensor-based manipulator
8. Integration of representation into goal-driven behavior-based robots
9. A reinforcement connectionist learning approach to robot path finding
10. Rapid, safe, and incremental learning of navigation strategies
11. Incremental acquisition of local networks for the control of autonomous robots
12. A reinforcement connectionist approach to robot path finding in non-maze-like environments
13. Experiments with reinforcement learning in problems with continuous state and action spaces
14. A reinforcement learning method for maximizing undiscounted rewards
15. Reinforcement learning with replacing eligibility traces
16. Learning to predict by the methods of temporal differences
17. Generalization in reinforcement learning: Successful examples using sparse coarse coding
18. Model-based average reward reinforcement learning
19. Reinforcement learning of multiple tasks using a hierarchical CMAC architecture
20. The role of exploration in learning control
21. Learning with delayed rewards