Inter-agent communication can significantly increase performance in multi-agent tasks that require co-ordination to achieve a shared goal. Prior work has shown that it is possible to learn inter-agent communication protocols using multi-agent reinforcement learning and message-passing network architectures. However, these models use an unconstrained broadcast communication model, in which an agent communicates with all other agents at every step, even when the task does not require it. In real-world applications, where communication may be limited by system constraints like bandwidth, power and network capacity, one might need to reduce the number of messages that are sent. In this work, we explore a simple method of minimizing communication while maximizing performance in multi-task learning: simultaneously optimizing a task-specific objective and a communication penalty. We show that the objectives can be optimized using Reinforce and the Gumbel-Softmax reparameterization. We introduce two techniques to stabilize training: 50% training and message forwarding. Training with the communication penalty on only 50% of the episodes prevents our models from turning off their outgoing messages. Second, repeating messages received previously helps models retain information, and further improves performance. With these techniques, we show that we can reduce communication by 75% with no loss of performance.
An approach of deep reinforcement learning for maximizing the net present value of stochastic projects
School of Finance and Business, Shanghai Normal University, China(金融与商业学院,上海Normal大学);School of Information and Mechanical and Electrical Engineering, Shanghai Normal University, China(信息与机械电子工程学院,上海Normal大学);School of Management, Northwestern Polytechnical University, Xi’an, China(管理学院,西北工业大学)
A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning
Aillis Inc.(Aillis公司);Department of Health Policy(健康政策部门);Public Health, Graduate School of Pharmaceutical Sciences, The University of Tokyo, Tokyo, Japan(公共卫生,药学研究生院,东京大学,东京,日本);Rist Inc.(Rist公司)
Genetic Algorithm enhanced by Deep Reinforcement Learning in parent selection mechanism and mutation : Minimizing makespan in permutation flow shop scheduling problems
Ecole Nationale Supérieure d'Informatique(国家高等信息学院)