Exploration and value function factorisation in single and multi-agent reinforcement learning
<p>The ability to learn from data is crucial in developing satisfactory solutions to many complex problems. In particular, in the design of intelligent agents that exist and interact with a complex environment in the pursuit of some goal. In this thesis we investigate some bottlenecks that can...
المؤلف الرئيسي: | Rashid, T |
---|---|
مؤلفون آخرون: | Whiteson, S |
التنسيق: | أطروحة |
اللغة: | English |
منشور في: |
2021
|
الموضوعات: |
مواد مشابهة
-
Monotonic value function factorisation for deep multi-agent reinforcement learning
حسب: Rashid, T, وآخرون
منشور في: (2020) -
QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning
حسب: Rashid, T, وآخرون
منشور في: (2018) -
Weighted QMIX: Expanding monotonic value function factorisation for deep multi−agent reinforcement learning
حسب: Rashid, T, وآخرون
منشور في: (2020) -
Rethinking Exploration and Experience Exploitation in Value-Based Multi-Agent Reinforcement Learning
حسب: Anatolii Borzilov, وآخرون
منشور في: (2025-01-01) -
Reinforcement Learning with Value Function Decomposition for Hierarchical Multi-Agent Consensus Control
حسب: Xiaoxia Zhu
منشور في: (2024-09-01)