AEMS: An Anytime Online Search Algorithm for Approximate Policy Refinement in Large POMDPs.
Stéphane RossBrahim Chaib-draaPublished in: IJCAI (2007)
Keyphrases
- search algorithm
- point based value iteration
- partially observable markov decision processes
- optimal policy
- online learning
- search space
- policy search
- real time
- policy gradient
- reinforcement learning
- partially observable
- distributed constraint optimization
- markov decision processes
- finite state
- policy iteration algorithm
- approximate solutions
- belief state
- state space
- exact solution
- branch and bound
- policy evaluation
- heuristic search
- multi agent
- learning algorithm