Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous Time.
Jeongho KimInsoon YangPublished in: L4DC (2020)
Keyphrases
- hamilton jacobi bellman
- optimal control
- reinforcement learning
- control problems
- dynamic programming
- state space
- dynamical systems
- nonlinear systems
- function approximation
- stochastic control
- learning rate
- policy iteration
- learning algorithm
- rl algorithms
- control strategy
- infinite horizon
- multi agent
- reinforcement learning algorithms
- optimal policy
- approximate dynamic programming
- control law
- temporal difference learning
- model free
- action selection
- brownian motion
- learning problems
- markov decision processes
- queueing systems
- markov chain
- machine learning