Transfer Learning for Multi-agent Coordination
نویسندگان
چکیده
Transfer learning leverages an agent’s experience in a source task in order to improve its performance in a related target task. Recently, this technique has received attention in reinforcement learning settings. Training a reinforcement learning agent on a suitable source task allows the agent to reuse this experience to significantly improve performance on more complex target problems. Currently, reinforcement learning transfer approaches focus almost exclusively on speeding up learning in single agent systems. In this paper we investigate the potential of applying transfer learning to the problem of agent coordination in multi-agent systems. The idea underlying our approach is that agents can determine how to deal with the presence of other agents in a relatively simple training setting. By then generalizing this knowledge, the agents can use this experience to speed up learning in more complex multi-agent learning tasks.
منابع مشابه
Voltage Coordination of FACTS Devices in Power Systems Using RL-Based Multi-Agent Systems
This paper describes how multi-agent system technology can be used as the underpinning platform for voltage control in power systems. In this study, some FACTS (flexible AC transmission systems) devices are properly designed to coordinate their decisions and actions in order to provide a coordinated secondary voltage control mechanism based on multi-agent theory. Each device here is modeled as ...
متن کاملOn Exponential Convergence of Coordination Learning Control for Multi-agent Formation ⋆
The exponential convergence problem is studied for coordination learning control of multi-agent formation under the switching network topology. A necessary and sufficient condition on exponential convergence is presented for coordination learning control algorithms of multi-agent formation tasks without any reference as prior knowledge. Moreover, it is shown that the developed results are effec...
متن کاملUtilizing Generalized Learning Automata for Finding Optimal Policies in MMDPs
Multi agent Markov decision processes (MMDPs), as the generalization of Markov decision processes to the multi agent case, have long been used for modeling multi agent system and are used as a suitable framework for Multi agent Reinforcement Learning. In this paper, a generalized learning automata based algorithm for finding optimal policies in MMDP is proposed. In the proposed algorithm, MMDP ...
متن کاملMulti-Agent Coordination in Open Environments
This paper proposes a new approach to multi-agent systems leveraging from recent advances in networking and reinforcement learning to scale up teamwork based on joint intentions. In this approach, teamwork is subsumed by the coordination of learning agents. The intuition behind this approach is that successful coordination at the global level generates opportunities for teamwork interactions at...
متن کاملMulti-agent learning in mobilized ad-hoc networks
In large, distributed systems such as mobilized ad-hoc networks, centralized learning of routing or movement policies may be impractical. We need to employ multi-agent learning algorithms that can learn independently, without the need for extensive coordination. Using only a simple coordination signals such as a global reward value, we show that reinforcement learning methods can be used to con...
متن کامل