Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Critic.
Behrad ToghiRodolfo ValienteDorsa SadighRamtin PedarsaniYaser P. FallahPublished in: CoRR (2021)
Keyphrases
- cooperative
- multi agent
- autonomous vehicles
- actor critic
- reinforcement learning
- multiagent systems
- single agent
- policy gradient
- path planning
- multi agent systems
- autonomous agents
- motion planning
- partially observable markov decision processes
- obstacle avoidance
- optimal control
- temporal difference
- multiple agents
- gradient method
- approximate dynamic programming
- robot control
- fuzzy control
- function approximation
- planning problems
- closed loop
- game theory
- state space
- mobile robot
- step size