POMDP Planning for Object Search in Partially Unknown Environment.
Yongbo ChenHanna KurniawatiPublished in: NeurIPS (2023)
Keyphrases
- partially observable markov decision process
- search algorithm
- initially unknown
- search space
- planning problems
- mobile robot
- heuristic search
- search strategy
- real time
- state space
- forward search
- belief space
- reinforcement learning
- belief state
- search strategies
- object model
- search methods
- partially observable
- partially observable markov decision processes
- optimal policy
- dynamic environments
- d objects
- data objects
- finite state
- action selection
- reward function
- planning under uncertainty
- np hard