Mixed Reinforcement Learning for Partially Observable Markov Decision Process.
Le Tien DungTakashi KomedaMotoki TakagiPublished in: CIRA (2007)
Keyphrases
- partially observable markov decision process
- reinforcement learning
- state and action spaces
- state space
- partially observable
- decision theoretic
- partially observable markov decision processes
- belief state
- markov decision processes
- action space
- multi agent
- function approximation
- markov decision problems
- average reward
- model free
- machine learning
- planning under uncertainty
- markov decision process
- temporal difference
- heuristic search
- optimal policy
- reinforcement learning algorithms
- learning agent
- finite state
- dynamical systems
- domain independent
- transfer learning