Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents.
Woojun KimYongjae ShinJongeui ParkYoungchul SungPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- multi agent
- intelligent agents
- action selection
- multi agent systems
- autonomous agents
- learning algorithm
- multiple agents
- learning agents
- agent architecture
- decision making
- machine learning
- artificial agents
- agent model
- agent systems
- multi agent reinforcement learning
- interacting agents
- deep learning
- social welfare
- optimal control
- ensemble methods
- resource allocation
- training set