Prise de décision en temps-réel pour des POMDP de grande taille.
Sébastien PaquetLudovic TobinBrahim Chaib-draaPublished in: Rev. d'Intelligence Artif. (2006)
Keyphrases
- partially observable markov decision process
- partially observable markov decision processes
- description logics
- reinforcement learning
- finite state
- dynamical systems
- model free reinforcement learning
- partially observable
- belief state
- state space
- continuous state
- optimal policy
- belief space
- hidden state
- decision problems
- markov decision processes
- decision theoretic
- dec pomdps
- partial observability
- multi agent
- markov decision process
- point based value iteration
- partially observable stochastic games
- markov decision problems
- reward function
- heuristic search
- decision making
- neural network