Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous Time.
Jeongho KimInsoon YangPublished in: CoRR (2019)
Keyphrases
- hamilton jacobi bellman
- optimal control
- reinforcement learning
- control problems
- dynamic programming
- nonlinear systems
- state space
- rl algorithms
- dynamical systems
- stochastic control
- learning rate
- policy iteration
- function approximation
- reinforcement learning algorithms
- multi agent
- learning algorithm
- control strategy
- brownian motion
- action selection
- model free
- temporal difference
- temporal difference learning
- approximate dynamic programming
- optimal policy
- average cost
- infinite horizon
- queueing systems