Multiagent POMDPs with asynchronous execution.
João V. MessiasMatthijs T. J. SpaanPedro U. LimaPublished in: AAMAS (2013)
Keyphrases
- multi agent
- distributed constraint optimization
- dec pomdps
- reinforcement learning
- partially observable markov decision
- multiagent systems
- planning under uncertainty
- cooperative
- single agent
- partially observable markov decision processes
- multi agent systems
- execution model
- belief state
- markov decision processes
- continuous state
- multiagent learning
- asynchronous communication
- dynamic programming
- decision trees
- neural network
- partially observable
- multiple agents
- plan generation
- autonomous agents
- optimal policy
- state space
- point based value iteration