Multiagent Learning Systems and Expert Agents
نویسندگان
چکیده
This paper focuses on two main research topics we axe investigating. First, we investigate how agents can learn strategic behavior in a teacher-learner model. The notion of the teacher here should be understood as a "trainer". We present the general teacher-learner model together with results from experiments performed in the traffic hghts domain. Second, we investigate how agents can learn to become experts, and eventually organize themselves appropriately for a range of tasks. The model is based on evolutionary processes that lead to organizations of experts. In our case, the organization emerges as a step prior to the execution of a task, and as a general process related to a range of problems in a domain. To explore these ideas, we designed and implemented a testbed based on the idea of the game of Life.
منابع مشابه
A Multiagent Reinforcement Learning algorithm to solve the Community Detection Problem
Community detection is a challenging optimization problem that consists of searching for communities that belong to a network under the assumption that the nodes of the same community share properties that enable the detection of new characteristics or functional relationships in the network. Although there are many algorithms developed for community detection, most of them are unsuitable when ...
متن کاملCounterfactual Exploration for Improving Multiagent Learning
In any single agent system, exploration is a critical component of learning. It ensures that all possible actions receive some degree of attention, allowing an agent to converge to good policies. The same concept has been adopted by multiagent learning systems. However, there is a fundamentally different dynamic in multiagent learning: each agent operates in a non-stationary environment, as a d...
متن کاملOn Convergence and Optimality of Best-Response Learning with Policy Types in Multiagent Systems
While many multiagent algorithms are designed for homogeneous systems (i.e. all agents are identical), there are important applications which require an agent to coordinate its actions without knowing a priori how the other agents behave. One method to make this problem feasible is to assume that the other agents draw their latent policy (or type) from a specific set, and that a domain expert c...
متن کاملLearning in Multiagent Systems: An Introduction from a Game-Theoretic Perspective
We introduce the topic of learning in multiagent systems. We first provide a quick introduction to the field of game theory, focusing on the equilibrium concepts of iterated dominance, and Nash equilibrium. We show some of the most relevant findings in the theory of learning in games, including theorems on fictitious play, replicator dynamics, and evolutionary stable strategies. The CLRI theory...
متن کاملCooperative Multiagent Learning
Cooperation and learning are two ways in which an agent can improve its performance. Cooperative Multiagent Learning is a framework to analyze the tradeoff between cooperation and learning in multiagent systems. We focus on multiagent systems where individual agents are capable of solving problems and learning using CBR (Case-based Reasoning). We present several collaboration strategies for age...
متن کاملGuest Editorial about Multiagent Learning
This special issue is on multiagent learning, that is, on learning that relies on or even requires the interaction among several intelligent agents. An agent is commonly understood as a computational or natural entity that can be viewed as perceiving in and acting upon its environment, as being autonomous in that its behavior is at least partially determined by its own experience, and as pursui...
متن کامل