A Q-learning algorithm for Markov decision processes with continuous state spaces.
Jiaqiao HuXiangyu YangJian-Qiang HuYijie PengPublished in: Syst. Control. Lett. (2024)
Keyphrases
- markov decision processes
- continuous state spaces
- learning algorithm
- reinforcement learning
- reinforcement learning algorithms
- state space
- action space
- finite state
- optimal policy
- continuous state
- policy iteration
- dynamic programming
- machine learning
- average cost
- machine learning algorithms
- finite horizon
- planning under uncertainty
- control problems
- learning problems
- learning tasks
- infinite horizon
- supervised learning
- partially observable markov decision processes
- learning agent
- multi agent
- least squares
- rl algorithms
- markov decision process
- transfer learning
- reward function
- temporal difference
- control strategy