Simulation With Learning Agents
Adaptive entities; Goal-based adaptation; Learning agents; Random neural networks; Reinforcement learning; Simulation
We propose that learning agents (LAs) be incorporated into simulation environments in order to model the adaptive behavior of hunans. These LAs adapt to specific circumstances and events daring the simulation run. They would select tasks to be accomplished among a given set of tusks as the simulation progresses, or synthesize tasks for themselves based on their observations of the environment and on information they may receive from other agents. We investigate an approach in which agents are assigned goals when the simulation starts and then pursue these goals autonomously and adoptively. During the simulation, agents progressively improve their ability to accomplish their goals effectively and safely. Agents learn from their own observations and from the experience of other agents with whom they exchange information. Each LA starts with a given representation of the simulation environment from which it progressively constructs its own internal representation and uses it to make decisions. This paper describes how learning neural nemorks can support this approach and shows that goal-based learning may be used effectively used in this context. An example simulation is presented in 'which agents represent manned vehicles; they are assigned the goal of traversing a dangerous metropolitan grid safely and rapidly using goal-based reinforcement learning with neural networks and compared to three other algorithms. © 2001 IEEE.
Proceedings of the IEEE
Number of Pages
Source API URL
Gelenbe, Erol; Şeref, Esin; and Zhiguang, X. U., "Simulation With Learning Agents" (2001). Scopus Export 2000s. 618.