Asymptotically Optimal Belief Space Planning in Discrete Partially-Observable Domains.
Janis Eric FreundCamille PhiquepalAndreas OrtheyMarc ToussaintPublished in: CoRR (2023)
Keyphrases
- belief space
- asymptotically optimal
- partially observable domains
- partially observable
- partially observable markov decision processes
- optimal policy
- belief state
- planning under uncertainty
- state space
- dynamical systems
- decision problems
- reinforcement learning
- markov decision processes
- sensing actions
- motion planning
- infinite horizon
- arrival rate
- finite state
- dynamic programming
- dynamic environments
- planning problems
- planning graph
- call center
- classical planning
- initial state
- learning algorithm
- sufficient conditions
- multi agent
- domain specific
- ai planning
- reward function
- planning process
- objective function
- long run
- orders of magnitude