Factored Online Planning in Many-Agent POMDPs.
Maris F. L. GaleslootThiago D. SimãoSebastian JungesNils JansenPublished in: AAAI (2024)
Keyphrases
- partially observable
- stochastic domains
- state space
- belief state
- partially observable markov decision process
- partially observable markov decision processes
- multi agent
- belief space
- action selection
- reinforcement learning
- multi agent systems
- decision theoretic
- online learning
- markov decision processes
- semantic web service composition
- dynamic environments
- single agent
- planning problems
- external events
- heuristic search
- software agents
- mobile agents
- autonomous agents
- planning domains
- dynamic bayesian networks
- goal directed
- multiagent systems
- incomplete knowledge
- world model
- partial observability
- markov decision problems
- decision problems
- planning under uncertainty
- ai planning
- reward function
- agent model
- dynamic programming
- search space
- agent technology
- point based value iteration
- plan execution
- intelligent agents
- information gathering
- distributed constraint optimization
- bayesian networks