Multi-Agent Recurrent Deterministic Policy Gradient with Inter-Agent Communication.
Joohyun ChoMingxi LiuYi ZhouRong-Rong ChenPublished in: ACSSC (2023)
Keyphrases
- agent communication
- multi agent
- policy gradient
- single agent
- reinforcement learning
- multi agent systems
- partially observable markov decision processes
- multiple agents
- optimal control
- function approximation
- multiagent systems
- cooperative
- gradient method
- agent architecture
- software agents
- autonomous agents
- reinforcement learning algorithms
- approximation methods
- intelligent agents
- speech acts
- variance reduction
- black box
- game theory
- action space
- average reward
- stochastic games
- machine learning