baller2vec++: A Look-Ahead Multi-Entity Transformer For Modeling Coordinated Agents
arXiv:2104.11980
Abstract
In many multi-agent spatiotemporal systems, agents operate under the influence of shared, unobserved variables (e.g., the play a team is executing in a game of basketball). As a result, the trajectories of the agents are often statistically dependent at any given time step; however, almost universally, multi-agent models implicitly assume the agents' trajectories are statistically independent at each time step. In this paper, we introduce baller2vec++, a multi-entity Transformer that can effectively model coordinated agents. Specifically, baller2vec++ applies a specially designed self-attention mask to a mixture of location and "look-ahead" trajectory sequences to learn the distributions of statistically dependent agent trajectories. We show that, unlike baller2vec (baller2vec++'s predecessor), baller2vec++ can learn to emulate the behavior of perfectly coordinated agents in a simulated toy dataset. Additionally, when modeling the trajectories of professional basketball players, baller2vec++ outperforms baller2vec by a wide margin.
References in corpus (12)
- Longformer: The Long-Document Transformer
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- Is Space-Time Attention All You Need for Video Understanding?
- Generating Long Sequences with Sparse Transformers
- Axial Attention in Multidimensional Transformers
- Reformer: The Efficient Transformer
- Big Bird: Transformers for Longer Sequences
- Argoverse: 3D Tracking and Forecasting with Rich Maps
- Temporal Graph Networks for Deep Learning on Dynamic Graphs
- Generating Long-term Trajectories Using Deep Hierarchical Networks
- Generating Multi-Agent Trajectories using Programmatic Weak Supervision
- baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modeling