Memory Bounded Open-Loop Planning in Large POMDPs using Thompson Sampling.
Thomy PhanLenz BelznerMarie KiermeierMarkus FriedrichKyrill SchmidClaudia Linnhoff-PopienPublished in: CoRR (2019)
Keyphrases
- open loop
- closed loop
- feedback control
- control system
- partially observable markov decision processes
- partially observable
- belief space
- reinforcement learning
- belief state
- inverted pendulum
- stability analysis
- planning problems
- predictive state representations
- markov decision processes
- control law
- dynamic programming
- point based value iteration
- control scheme
- optimal control
- dynamical systems
- monte carlo
- state space
- expert systems
- adaptive control