MAT-DQN: Toward Interpretable Multi-agent Deep Reinforcement Learning for Coordinated Activities.
Yoshinari MotokawaToshiharu SugawaraPublished in: ICANN (4) (2021)
Keyphrases
- multi agent
- reinforcement learning
- multi agent reinforcement learning
- cooperative
- multi agent systems
- multiagent systems
- function approximation
- learning agents
- intelligent agents
- state space
- cooperative agents
- heterogeneous agents
- single agent
- learning algorithm
- coordination mechanisms
- multi agent environments
- activity recognition
- autonomous agents
- coalition formation
- temporal difference
- daily life
- agent oriented
- medial axis
- multiple agents
- deep learning
- action space
- human activities
- dynamic programming
- classification rules
- optimal policy