Traffic-signal control reinforcement learning approach for continuous-time Markov games.
Román Aragon-GómezJulio B. ClempnerPublished in: Eng. Appl. Artif. Intell. (2020)
Keyphrases
- markov games
- traffic signal control
- reinforcement learning
- reinforcement learning algorithms
- state space
- markov decision processes
- optimal control
- markov decision process
- control problems
- function approximation
- multiagent reinforcement learning
- markov chain
- model free
- optimal policy
- learning algorithm
- finite state
- dynamic programming
- multi agent
- dynamical systems
- policy iteration
- temporal difference
- action selection
- machine learning
- learning agent
- temporal difference learning
- cooperative
- robot control
- search space
- control policy
- markov decision problems