Policy Gradient Based Control of a Pneumatic Actuator Enhanced with Monte Carlo Tree Search.
Balint KovariTamás BécsiÁdám SzabóSzilárd AradiPublished in: ICMRE (2020)
Keyphrases
- control system
- monte carlo tree search
- monte carlo
- control method
- bayesian reinforcement learning
- optimal policy
- closed loop
- control strategy
- control strategies
- tree search algorithm
- pid control
- monte carlo search
- decision problems
- convergence rate
- optimal control
- control algorithm
- reinforcement learning
- control scheme
- control problems
- force control