Policy Gradient-based Model Free Optimal LQG Control with a Probabilistic Risk Constraint.
Arunava NahaSubhrakanti DeyPublished in: CoRR (2024)
Keyphrases
- optimal control
- model free
- reinforcement learning
- policy iteration
- control policy
- infinite horizon
- rl algorithms
- impedance control
- dynamic programming
- optimal policy
- policy evaluation
- average reward
- control strategy
- function approximation
- control policies
- average cost
- linear quadratic
- reinforcement learning algorithms
- temporal difference
- bayesian networks
- markov decision process
- action selection
- control system
- state space
- markov decision problems
- motion planning
- markov decision processes
- supervised learning
- least squares
- probabilistic model