Reinforcement Learning for Traffic Signal Control in Hybrid Action Space.
Haoqing LuoYiming BieSheng JinPublished in: IEEE Trans. Intell. Transp. Syst. (2024)
Keyphrases
- action space
- reinforcement learning
- traffic signal control
- state space
- markov decision processes
- state and action spaces
- continuous state
- real valued
- function approximation
- continuous state spaces
- action selection
- reinforcement learning methods
- state action
- reinforcement learning algorithms
- learning algorithm
- dynamic programming
- stochastic processes
- optimal policy
- multi agent
- markov decision process
- markov decision problems
- single agent
- function approximators
- policy search