Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling
arXiv:2007.03155 · doi:10.1016/j.neunet.2023.11.068
Abstract
Extracting the rules of real-world multi-agent behaviors is a current challenge in various scientific and engineering fields. Biological agents independently have limited observation and mechanical constraints; however, most of the conventional data-driven models ignore such assumptions, resulting in lack of biological plausibility and model interpretability for behavioral analyses. Here we propose sequential generative models with partial observation and mechanical constraints in a decentralized manner, which can model agents' cognition and body dynamics, and predict biologically plausible behaviors. We formulate this as a decentralized multi-agent imitation-learning problem, leveraging binary partial observation and decentralized policy models based on hierarchical variational recurrent neural networks with physical and biomechanical penalties. Using real-world basketball and soccer datasets, we show the effectiveness of our method in terms of the constraint violations, long-term trajectory prediction, and partial observation. Our approach can be used as a multi-agent simulator to generate realistic trajectories using real-world data.
arXiv comment17 pages with 7 figures and 4 tables, accepted in Neural Networks
References in corpus (26)
- Adam: A Method for Stochastic Optimization
- Auto-Encoding Variational Bayes
- Neural Machine Translation by Jointly Learning to Align and Translate
- Social Force Model for Pedestrian Dynamics
- Interaction Ruling Animal Collective Behaviour Depends on Topological rather than Metric Distance: Evidence from a Field Study
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- A Recurrent Latent Variable Model for Sequential Data
- Learning Attentional Communication for Multi-Agent Cooperation
- Actor-Attention-Critic for Multi-Agent Reinforcement Learning
- Neural Relational Inference for Interacting Systems
- Composing graphical models with neural networks for structured representations and fast inference
- Sequential Neural Models with Stochastic Layers
- A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
- Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
- Generating Long-term Trajectories Using Deep Hierarchical Networks
- Social Attention for Autonomous Decision-Making in Dense Traffic
- Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPG
- Generating Multi-Agent Trajectories using Programmatic Weak Supervision
- Data-driven Analysis for Understanding Team Sports Behaviors
- Dynamic mode decomposition in vector-valued reproducing kernel Hilbert spaces for extracting dynamical structure among observables
- Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion
- Tighter Variational Bounds are Not Necessarily Better
- Learning recurrent representations for hierarchical behavior modeling
- Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causality
- Estimating counterfactual treatment outcomes over time in complex multiagent scenarios
- BasketballGAN: Generating Basketball Play Simulation Through Sketching