Rating Continuous Actions in Spatial Multi-Agent Problems
We study credit assignment problems in spatial multi-agent environments where agents pursue a joint objective. On the example of soccer, we rate the movements of individual players with respect to their potential for staging a successful attack. We propose a purely data-driven approach to simultaneously learn a model of agent movements as well as their ratings via an agent-centric deep reinforcement learning framework. Our model allows for efficient learning and sampling of ratings in the continuous action space. We empirically observe on historic soccer data that the model accurately rates agent movements w.r.t. their relative contribution to the collective goal.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Generating Origin-Destination Matrices in Neural Spatial Interaction Models
Agent-based models (ABMs) are proliferating as decision-making tools across policy areas in transportation, economics, and epidemiology. In these models, a central object of interest is the discrete origin-destination ma…
Agent-based model inverse problemDecision MakingAction valuation of on- and off-ball soccer players based on multi-agent deep reinforcement learning
Analysis of invasive sports such as soccer is challenging because the game situation changes continuously in time and space, and multiple agents individually recognize the game situation and make decisions. Previous stud…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningKnowledge-Informed Multi-Agent Trajectory Prediction at Signalized Intersections for Infrastructure-to-Everything
Multi-agent trajectory prediction at signalized intersections is crucial for developing efficient intelligent transportation systems and safe autonomous driving systems. Due to the complexity of intersection scenarios an…
Autonomous DrivingGraph AttentionPredictionTrajectory PredictionSTAGED: A Multi-Agent Neural Network for Learning Cellular Interaction Dynamics
The advent of single-cell technology has significantly improved our understanding of cellular states and subpopulations in various tissues under normal and diseased conditions by employing data-driven approaches such as …
Multi-Timescale, Gradient Descent, Temporal Difference Learning with Linear Options
Deliberating on large or continuous state spaces have been long standing challenges in reinforcement learning. Temporal Abstraction have somewhat made this possible, but efficiently planing using temporal abstraction sti…
Reinforcement LearningReinforcement Learning (RL)