Adaptive internal state space construction method for reinforcement learning of a real-world agent.
Kazuyuki SamejimaTakashi OmoriPublished in: Neural Networks (1999)
Keyphrases
- state space
- reinforcement learning
- synthetic data
- multi agent
- real world
- clustering method
- significant improvement
- partially observable
- markov decision processes
- high accuracy
- dynamic programming
- cost function
- pairwise
- preprocessing
- computational complexity
- dynamic environments
- detection method
- segmentation method
- decision making
- data sets