On-Robot Bayesian Reinforcement Learning for POMDPs.
Hai NguyenSammie KattYuchen XiaoChristopher AmatoPublished in: IROS (2023)
Keyphrases
- bayesian reinforcement learning
- partially observable markov decision processes
- optimal policy
- reinforcement learning
- monte carlo tree search
- mobile robot
- finite state
- dynamical systems
- humanoid robot
- robot navigation
- dynamic programming
- planning under uncertainty
- belief state
- state space
- markov decision processes
- decision problems
- path planning
- markov decision problems
- multi agent
- monte carlo
- partially observable
- infinite horizon
- function approximation
- sufficient conditions