Convex Q-Learning, Part 1: Deterministic Optimal Control.
Prashant G. MehtaSean P. MeynPublished in: CoRR (2020)
Keyphrases
- optimal control
- reinforcement learning
- dynamic programming
- control problems
- policy iteration
- function approximation
- actor critic
- state space
- control strategy
- rl algorithms
- feedback control
- convex optimization
- risk sensitive
- optimal control problems
- learning algorithm
- infinite horizon
- model free
- reinforcement learning algorithms
- class of nonlinear systems
- lyapunov function
- brownian motion
- action selection
- markov decision processes
- learning rate
- stochastic control
- machine learning
- average cost
- temporal difference
- data mining
- convex sets
- linear quadratic