Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning.
Harley WiltzerDavid MegerMarc G. BellemarePublished in: CoRR (2022)
Keyphrases
- hamilton jacobi bellman
- optimal control
- reinforcement learning
- control problems
- dynamic programming
- stochastic control
- approximate dynamic programming
- infinite horizon
- control strategy
- state space
- dynamical systems
- optimal policy
- machine learning
- brownian motion
- rl algorithms
- queueing systems
- control law
- function approximation
- adaptive control
- reinforcement learning algorithms
- learning algorithm
- temporal difference
- average cost
- supervised learning
- policy iteration
- model free
- neural network
- markov decision processes