Evolutionary Multiagent Transfer Learning With Model-Based Opponent Behavior Prediction
نویسندگان
چکیده
This article embarks a study on multiagent transfer learning (TL) for addressing the specific challenges that arise in complex systems where agents have different or even competing objectives. Specifically, beyond essential backbone of state-of-the-art evolutionary TL framework (eTL), this presents novel with prediction (eTL-P) as an upgrade over existing eTL to endow abilities interact their opponents effectively by building candidate models and accordingly predicting behavioral strategies. To reduce complexity models, eTL-P constructs monotone submodular function, which facilitates select Top- ${K}$ from all available based representativeness terms coverage well reward diversity. also integrates social selection mechanisms identify better-performing partners, thus improving performance reducing behavior reusing useful knowledge respect partners’ mind universes. Experiments partner-opponent minefield navigation task (PO-MNT) shown exhibits superiority achieving higher capability efficiency multiple when compared approaches.
منابع مشابه
Improving Opponent Intelligence through Offline Evolutionary Learning
Artificially intelligent opponents in commercial computer games are almost exclusively controlled by manuallydesigned scripts. With increasing game complexity, the scripts tend to become quite complex too. As a consequence they often contain “holes” that can be exploited by the human player. The research question addressed in this paper reads: How can evolutionary learning techniques be applied...
متن کاملMultiagent Learning for Open Systems: A Study in Opponent Classification
Open systems are becoming increasingly important in a variety of distributed, networked computer applications. Their characteristics, such as agent diversity, heterogeneity and fluctuation, confront multiagent learning with new challenges. This paper presents the interaction learning meta-architecture InFFrA as one possible answer to these challenges, and introduces the opponent classification ...
متن کاملTransfer Learning for Multiagent Reinforcement Learning Systems
Reinforcement learning methods have successfully been applied to build autonomous agents that solve many sequential decision making problems. However, agents need a long time to learn a suitable policy, specially when multiple autonomous agents are in the environment. This research aims to propose a Transfer Learning (TL) framework to accelerate learning by exploiting two knowledge sources: (i)...
متن کاملAdaptive automata model for learning opponent behavior based on genetic algorithms
The purpose of this research is to study how genetic algorithms (GA's) are applied in the field of Game Theory. GA's are effective approaches for machine learning and optimization problems. In this work, genetic algorithm is utilized to determine the behavior of an opponent in Prisoners’ Dilemma. The opponent behavior will be modeled by means of adaptive automaton. The basic problem of this stu...
متن کاملLearning with Opponent-Learning Awareness
Multi-agent settings are quickly gathering importance in machine learning. Beyond a plethora of recent work on deep multi-agent reinforcement learning, hierarchical reinforcement learning, generative adversarial networks and decentralized optimization can all be seen as instances of this setting. However, the presence of multiple learning agents in these settings renders the training problem no...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE transactions on systems, man, and cybernetics
سال: 2021
ISSN: ['1083-4427', '1558-2426']
DOI: https://doi.org/10.1109/tsmc.2019.2958846