An On-Line POMDP Solver for Continuous Observation Spaces.
Marcus HörgerHanna KurniawatiPublished in: CoRR (2020)
Keyphrases
- discrete data
- reinforcement learning
- finite state
- state space
- continuous action
- partially observable markov decision processes
- action space
- continuous data
- continuous state
- bayesian networks
- monte carlo
- planning problems
- optimal policy
- infinite horizon
- partially observable
- markov decision process
- multi agent
- partial observability