A5072418736- Topic Modeling
- Advanced Text Analysis Techniques
- Natural Language Processing Techniques
- Reinforcement Learning in Robotics
- Evolutionary Game Theory and Cooperation
- Data Quality and Management
- Opinion Dynamics and Social Influence
- Web Data Mining and Analysis
- Sentiment Analysis and Opinion Mining
- Evolution and Genetic Dynamics
CEA LIST
2017-2021
Université Paris-Saclay
2021
Commissariat à l'Énergie Atomique et aux Énergies Alternatives
2017-2021
Integra (United States)
2020
Laboratoire des signaux et systèmes
2019
University of Tartu
2015-2017
Evolution of cooperation and competition can appear when multiple adaptive agents share a biological, social, or technological niche. In the present work we study how emerge between autonomous that learn by reinforcement while using only their raw visual input as state representation. particular, extend Deep Q-Learning framework to multiagent environments investigate interaction two learning in well-known video game Pong. By manipulating classical rewarding scheme Pong show competitive...
Multiagent systems appear in most social, economical, and political situations. In the present work we extend Deep Q-Learning Network architecture proposed by Google DeepMind to multiagent environments investigate how two agents controlled independent Q-Networks interact classic videogame Pong. By manipulating classical rewarding scheme of Pong demonstrate competitive collaborative behaviors emerge. Competitive learn play score efficiently. Agents trained under schemes find an optimal...