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