Single-Agent Actor Critic for Decentralized Cooperative Driving.
Shengchao YanLukas KönigWolfram BurgardPublished in: CoRR (2024)
Keyphrases
- single agent
- cooperative
- policy gradient
- multi agent
- actor critic
- reinforcement learning
- multi agent systems
- dec pomdps
- multiple agents
- optimal control
- stochastic games
- approximate dynamic programming
- neuro fuzzy
- temporal difference
- dynamic environments
- function approximation
- reinforcement learning algorithms
- game theory
- path finding
- partially observable markov decision processes
- learning agent
- state space
- action space
- gradient method