Heuristically accelerated reinforcement learning modularization for multi-agent multi-objective problems

2014 ◽  
Vol 41 (2) ◽  
pp. 551-562 ◽  
Author(s):  
Leonardo Anjoletto Ferreira ◽  
Carlos Henrique Costa Ribeiro ◽  
Reinaldo Augusto da Costa Bianchi
Keyword(s):  
Reinforcement Learning ◽  
Multi Objective ◽  
Multi Agent

scholarly journals Scalarized Q Multi-Objective Reinforcement Learning for Area Coverage Control and Light Control Implementation

2018 ◽  
Vol 16 (2) ◽  
pp. 72-82
Author(s):  
Akkhachai Phuphanin ◽  
Wipawee Usaha
Keyword(s):  
Reinforcement Learning ◽  
Energy Consumption ◽  
Area Coverage ◽  
Coverage Area ◽  
Lighting Control ◽  
Multi Objective ◽  
Coverage Control ◽  
Control Schemes ◽  
Multi Agent ◽  
Testbed Experiments

Coverage control is crucial for the deployment of wireless sensor networks (WSNs). However, most coverage control schemes are based on single objective optimization such as coverage area only, which do not consider other contradicting objectives such as energy consumption, the number of working nodes, wasteful overlapping areas. This paper proposes on a Multi-Objective Optimization (MOO) coverage control called Scalarized Q Multi-Objective Reinforcement Learning (SQMORL). The two objectives are to achieve the maximize area coverage and to minimize the overlapping area to reduce energy consumption. Performance evaluation is conducted for both simulation and multi-agent lighting control testbed experiments. Simulation results show that SQMORL can obtain more efficient area coverage with fewer working nodes than other existing schemes.  The hardware testbed results show that SQMORL algorithm can find the optimal policy with good accuracy from the repeated runs.

scholarly journals Multi-Objective Workflow Scheduling With Deep-Q-Network-Based Multi-Agent Reinforcement Learning

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 39974-39982 ◽  
Author(s):  
Yuandou Wang ◽  
Hang Liu ◽  
Wanbo Zheng ◽  
Yunni Xia ◽  
Yawen Li ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Workflow Scheduling ◽  
Multi Objective ◽  
Multi Agent

scholarly journals Multi-Objective Optimization of Differentiated Urban Ring Road Bus Lines and Fares Based on Travelers’ Interactive Reinforcement Learning

Symmetry ◽  
2021 ◽  
Vol 13 (12) ◽  
pp. 2301
Author(s):  
Xueyan Li ◽  
Xin Zhu ◽  
Baoyu Li
Keyword(s):  
Reinforcement Learning ◽  
Traffic Management ◽  
Programming Model ◽  
Solution Algorithm ◽  
Travel Choice ◽  
Agent Model ◽  
Ring Road ◽  
Multi Objective ◽  
Multi Agent ◽  
Upper Level

This paper proposes a new multi-objective bi-level programming model for the ring road bus lines and fare design problems. The proposed model consists of two layers: the traffic management operator and travelers. In the upper level, we propose a multi-objective bus lines and fares optimization model in which the operator’s profit and travelers’ utility are set as objective functions. In the lower level, evolutionary multi agent model of travelers’ bounded rational reinforcement learning with social interaction is introduced. A solution algorithm for the multi-objective bi-level programming is developed on the basis of the equalization algorithm of OD matrix. A numerical example based on a real case was conducted to verify the proposed models and solution algorithm. The computational results indicated that travel choice models with different degrees of rationality significantly changed the optimization results of bus lines and the differentiated fares; furthermore, the multi-objective bi-level programming in this paper can generate the solution to reduce the maximum section flow, increase the profit, and reduce travelers’ generalized travel cost.

Reward shaping for knowledge-based multi-objective multi-agent reinforcement learning

2018 ◽  
Vol 33 ◽  
Author(s):  
Patrick Mannion ◽  
Sam Devlin ◽  
Jim Duggan ◽  
Enda Howley
Keyword(s):  
Reinforcement Learning ◽  
Credit Assignment ◽  
Multi Objective ◽  
Knowledge Based ◽  
Learning Speed ◽  
Reward Shaping ◽  
Multi Agent ◽  
Single Objective ◽  
Real World Problems

AbstractThe majority of multi-agent reinforcement learning (MARL) implementations aim to optimize systems with respect to a single objective, despite the fact that many real-world problems are inherently multi-objective in nature. Research into multi-objective MARL is still in its infancy, and few studies to date have dealt with the issue of credit assignment. Reward shaping has been proposed as a means to address the credit assignment problem in single-objective MARL, however it has been shown to alter the intended goals of a domain if misused, leading to unintended behaviour. Two popular shaping methods are potential-based reward shaping and difference rewards, and both have been repeatedly shown to improve learning speed and the quality of joint policies learned by agents in single-objective MARL domains. This work discusses the theoretical implications of applying these shaping approaches to cooperative multi-objective MARL problems, and evaluates their efficacy using two benchmark domains. Our results constitute the first empirical evidence that agents using these shaping methodologies can sample true Pareto optimal solutions in cooperative multi-objective stochastic games.

Sign in / Sign up

Export Citation Format

Share Document