Solving Stabilize-Avoid Optimal Control via Epigraph Form and Deep Reinforcement Learning.
Oswin SoChuchu FanPublished in: CoRR (2023)
Keyphrases
- optimal control
- reinforcement learning
- control problems
- dynamic programming
- infinite horizon
- hamilton jacobi bellman
- feedback control
- control strategy
- actor critic
- optimal control problems
- risk sensitive
- control law
- class of nonlinear systems
- policy iteration algorithm
- brownian motion
- function approximation
- lyapunov function
- optimal policy
- reinforcement learning algorithms
- markov decision processes
- state space
- real time
- rl algorithms
- average cost
- markov decision problems