Belief-State Query Policies for Planning With Preferences Under Partial Observability.
Daniel BramblettSiddharth SrivastavaPublished in: CoRR (2024)
Keyphrases
- partial observability
- belief state
- partially observable markov decision processes
- belief space
- partially observable
- state space
- planning under uncertainty
- belief revision
- planning problems
- planning under partial observability
- markov decision problems
- finite state
- markov decision process
- dynamical systems
- optimal policy
- reinforcement learning
- dynamic bayesian networks
- heuristic search
- orders of magnitude
- reward function
- incomplete information
- decision problems
- markov decision processes