Inverse Optimal Control with Discount Factor for Continuous and Discrete-Time Control-Affine Systems and Reinforcement Learning.
Luis RodriguesPublished in: CoRR (2022)
Keyphrases
- optimal control
- optimal control problems
- reinforcement learning
- control problems
- control strategy
- feedback control
- dynamic programming
- linear quadratic
- infinite horizon
- average cost
- control law
- real time
- markov decision processes
- optimal policy
- neural network
- partially observable
- average reward
- markov decision problems
- policy gradient
- markov chain