Multi-Agent Deep Reinforcement Learning in Vehicular OCC.
Amirul IslamLeila MusavianNikolaos ThomosPublished in: VTC Spring (2022)
Keyphrases
- reinforcement learning
- multi agent
- single agent
- state space
- function approximation
- multi agent systems
- learning agents
- intelligent agents
- reinforcement learning algorithms
- multi agent environments
- multi agent reinforcement learning
- learning algorithm
- software agents
- reinforcement learning agents
- temporal difference
- traffic flow
- model free
- learning problems
- markov decision processes
- multiple agents
- machine learning
- action selection
- reinforcement learning methods
- optimal policy
- data dissemination
- robot control
- state abstraction
- dynamic programming
- supervised learning
- action space
- learning process
- multiagent systems
- cooperative
- team formation
- control policy
- transition model
- multi agent coordination
- heterogeneous agents
- temporal difference learning
- deep learning
- cognitive model
- dynamical systems
- optimal control