Online Planning in POMDPs with State-Requests.
Raphaël AvalosEugenio BargiacchiAnn NowéDiederik M. RoijersFrans A. OliehoekPublished in: CoRR (2024)
Keyphrases
- belief state
- partially observable markov decision processes
- state space
- partially observable
- predictive state representations
- reinforcement learning
- markov decision processes
- stochastic domains
- online learning
- dynamical systems
- belief revision
- planning under uncertainty
- state variables
- planning problems
- real time
- multi agent systems
- search algorithm
- web services
- distributed constraint optimization
- e learning