Labeling Q-learning in hidden state environments.
Haeyeon LeeHiroyuki KamayaKenichi AbePublished in: Artif. Life Robotics (2002)
Keyphrases
- hidden state
- reinforcement learning
- markov models
- hidden markov models
- function approximation
- state space
- image segmentation
- partially observable
- dynamical systems
- learning algorithm
- fully observable
- maximum entropy
- dynamic environments
- multi agent
- machine learning
- markov decision processes
- higher order
- dynamic programming