Solving Challenging Control Problems Using Two-Staged Deep Reinforcement Learning.
Nitish SontakkeSehoon HaPublished in: CoRR (2021)
Keyphrases
- control problems
- reinforcement learning
- optimal control
- hamilton jacobi bellman
- function approximation
- markov decision problems
- state space
- queueing systems
- reinforcement learning methods
- optimal policy
- adaptive control
- model free
- learning algorithm
- machine learning
- temporal difference
- reinforcement learning algorithms
- least squares
- continuous state spaces
- learning problems
- markov decision processes
- dynamic programming
- stochastic control