V2V Cooperative Sensing using Reinforcement Learning with Action Branching.
Mohamed K. Abdel-AzizCristina PerfectoSumudu SamarakoonMehdi BennisPublished in: ICC (2021)
Keyphrases
- cooperative
- reinforcement learning
- action selection
- action space
- multi agent
- partially observable domains
- multi agent reinforcement learning
- joint action
- sensor networks
- transition model
- reward shaping
- function approximation
- multiagent reinforcement learning
- learning algorithm
- state action
- state space
- human actions
- cooperative learning
- model free
- learning process
- reinforcement learning algorithms
- fitted q iteration
- branch and bound
- transfer learning
- real time
- temporal difference
- robotic control
- learning classifier systems
- function approximators
- markov decision process
- reward function
- activity recognition
- optimal policy
- supervised learning
- multi agent systems
- search algorithm
- neural network