Factored Online Planning in Many-Agent POMDPs.
Maris F. L. GaleslootThiago D. SimãoSebastian JungesNils JansenPublished in: CoRR (2023)
Keyphrases
- stochastic domains
- partially observable
- belief state
- state space
- partially observable markov decision processes
- multi agent
- partially observable markov decision process
- decision theoretic
- reinforcement learning
- multi agent systems
- belief space
- goal directed
- action selection
- semantic web service composition
- single agent
- planning problems
- reactive agents
- markov decision processes
- markov decision problems
- planning process
- online learning
- partial observations
- multiple agents
- dynamical systems
- external events
- world model
- heuristic search
- incomplete knowledge
- partial observability
- point based value iteration
- planning under uncertainty
- factored markov decision processes
- autonomous agents
- software agents
- agent model
- markov decision process
- mobile agents
- initially unknown
- decision making
- infinite horizon
- decision problems
- belief revision
- search algorithm