Analysing Congestion Problems in Multi-agent Reinforcement Learning
نویسندگان
چکیده
We extend the study of congestion problems to a more realistic scenario, the Road Network Domain (RND), where the resources are no longer independent, but rather part of a network, thus choosing one path will also impact the load of another one having common road segments. We demonstrate the application of state-of-the-art multi-agent reinforcement learning methods for this new congestion model and analyse their performance. RND allows us to highlight an important limitation of resource abstraction and show that the difference rewards approach manages to better capture and inform the agents about the dynamics of the environment.
منابع مشابه
Co-learning Multi-agent Congestion Control for High-Speed Networks
In this paper, we present an adaptive multi-agent reinforcement learning method for solving congestion control problems on high-speed networks. Traditional reactive congestion control regulates source rate in terms of queue length restricted to a predefined threshold. However, the determination of the congested threshold and sending rate is difficult and inaccurate due to the dynamic nature of ...
متن کاملResource Abstraction for Reinforcement Learning in Multiagent Congestion Problems
Real-world congestion problems (e.g. traffic congestion) are typically very complex and large-scale. Multiagent reinforcement learning (MARL) is a promising candidate for dealing with this emerging complexity by providing an autonomous and distributed solution to these problems. However, there are three limiting factors that affect the deployability of MARL approaches to congestion problems. Th...
متن کاملAgent Reward Shaping for Alleviating Traffic Congestion
Traffic congestion problems provide a unique environment to study how multi-agent systems promote desired system level behavior. What is particularly interesting in this class of problems is that no individual action is intrinsically “bad” for the system but that combinations of actions among agents lead to undesirable outcomes. As a consequence, agents need to learn how to coordinate their act...
متن کاملReinforcement Learning of Traffic Light Controllers Adapting to Traffic Congestion
Due to the increasing amounts of traffic in and around urban areas there is a growing need for intelligent traffic lights that optimize traffic flow. In this paper we describe the optimization of traffic light controllers using a multi-agent, model-based reinforcement learning or approximate real-time dynamic programming approach. Our methods optimize individual traffic lights locally, but the ...
متن کاملOnline Learning for Multi-Agent Local Navigation
In this paper, we present an adaptive framework for improving the local navigation in multi-agent simulations. Our framework uses techniques from Reinforcement Learning allowing the agents to adapt their behavior online while the simulation is still running. It is general and can be easily combined with existing schemes for local navigation. As an example, we demonstrate its application using t...
متن کامل