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