Balancing Exploration and Exploitation in Agent Learning
نویسندگان
چکیده
The issue of controlling the ratio of exploration and exploitation in agent learning in dynamic environments provides a continuing challenge in the application of agent learning techniques. Methods to control this ratio in a manner that mimics human behavior are required for use in the representation of human behavior, which seek to constrain agent learning mechanisms in a manner similar to that observed in human cognition. This paper describes the use of two novel methods for adjusting the exploration and exploitation ratio of agents using a Cultural Geography (CG) Model.
منابع مشابه
Learning to Explore and Exploit in POMDPs
A fundamental objective in reinforcement learning is the maintenance of a proper balance between exploration and exploitation. This problem becomes more challenging when the agent can only partially observe the states of its environment. In this paper we propose a dual-policy method for jointly learning the agent behavior and the balance between exploration exploitation, in partially observable...
متن کاملExploration and Exploitation in Visuomotor Prediction of Autonomous Agents
This paper discusses various techniques to let an agent learn how to predict the effects of its own actions on its sensor data autonomously, and their usefulness to apply them to visual sensors. An Extreme Learning Machine is used for visuomotor prediction, while various autonomous control techniques that can aid the prediction process by balancing exploration and exploitation are discussed and...
متن کاملAdaptive Load Balancing : A Study in Multi - AgentLearningAndrea
We study the process of multi-agent reinforcement learning in the context of load balancing in a distributed system, without use of either central coordination or explicit communication. We rst deene a precise framework in which to study adaptive load balancing, important features of which are its stochastic nature and the purely local information available to individual agents. Given this fram...
متن کاملUsing DCOPs to Balance Exploration and Exploitation in Time-Critical Domains
Substantial work has investigated balancing exploration and exploitation, but relatively little has addressed this tradeoff in the context of coordinated multi-agent interactions. This paper introduces a class of problems in which agents must maximize their on-line reward, a decomposable function dependent on pairs of agent’s decisions. Unlike previous work, agents must both learn the reward fu...
متن کاملAdaptive Load Balancing: A Study in Multi-Agent Learning
We study the process of multi-agent reinforcement learning in the context of load balancing in a distributed system, without use of either central coordination or explicit communication. We rst de ne a precise framework in which to study adaptive load balancing, important features of which are its stochastic nature and the purely local information available to individual agents. Given this fram...
متن کامل