Improving Sample Efficiency and Multi-Agent Communication in RL-based Train Rescheduling
We present preliminary results from our sixth placed entry to the Flatland international competition for train rescheduling, including two improvements for optimized reinforcement learning (RL) training efficiency, and two hypotheses with respect to the prospect of deep RL for complex real-world control tasks: first, that current state of the art policy gradient methods seem inappropriate in the domain of high-consequence environments; second, that learning explicit communication actions (an emerging machine-to-machine language, so to speak) might offer a remedy. These hypotheses need to be confirmed by future work. If confirmed, they hold promises with respect to optimizing highly efficient logistics ecosystems like the Swiss Federal Railways railway network.
Code (0)
등록된 구현이 없습니다.
Tasks
Policy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Fault-tolerant control of random switching topology multi-agent system based on event triggering
In this paper, the formation control of multi-agent systems in random switching communication topology is studied, and the problem of excessive bandwidth and low control efficiency among multi-agents is solved. For nonli…
Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis
Actor-critic (AC) algorithms have been widely adopted in decentralized multi-agent systems to learn the optimal joint control policy. However, existing decentralized AC algorithms either do not preserve the privacy of ag…
CoDreamer: Communication-Based Decentralised World Models
Sample efficiency is a critical challenge in reinforcement learning. Model-based RL has emerged as a solution, but its application has largely been confined to single-agent scenarios. In this work, we introduce CoDreamer…
Near Optimal Best Arm Identification for Clustered Bandits
This work investigates the problem of best arm identification for multi-agent multi-armed bandits. We consider $N$ agents grouped into $M$ clusters, where each cluster solves a stochastic bandit problem. The mapping betw…
ClusteringComputational EfficiencyMulti-Armed BanditsDAIN: Dynamic Agent-Based Interaction Network for Efficient and Collaborative Multimodal Reasoning
Current multimodal fusion approaches, particularly those based on static Mixture-of-Experts (MoE) architectures, often struggle to provide the adaptive and efficient collaborative reasoning required by complex real-world…
Computational EfficiencyMultimodal Reasoning