SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems.
Oubo MaYuwen PuLinkang DuYang DaiRuo WangXiaolei LiuYingcai WuShouling JiPublished in: CoRR (2024)
Keyphrases
- learning systems
- partially observed
- multi agent
- reinforcement learning
- optimal policy
- american football
- learning process
- machine learning
- resolve conflicts
- multiagent systems
- learning environment
- computer supported
- fitted q iteration
- partially observable markov decision processes
- learning materials
- multi agent systems
- learning resources
- learning styles
- reinforcement learning agents
- markov decision processes
- multiple agents
- human learning
- learning algorithm
- adaptive systems
- statistical machine learning
- game playing
- multi agent learning
- collective learning
- team formation
- state space