Run-Time Improvement of Point-Based POMDP Policies.
Minlue WangRichard DeardenPublished in: IJCAI (2013)
Keyphrases
- partially observable markov decision processes
- optimal policy
- point based value iteration
- markov decision process
- reinforcement learning
- finite state
- markov decision processes
- model free reinforcement learning
- state space
- continuous state
- partially observable stochastic games
- multi agent
- partially observable
- dec pomdps
- long run
- dynamical systems
- dynamic programming
- neural network
- control policies
- belief space
- belief state
- revenue management
- predictive state representations
- bayesian reinforcement learning
- machine learning