DeepAI AI Chat
Log In Sign Up

baller2vec++: A Look-Ahead Multi-Entity Transformer For Modeling Coordinated Agents

by   Michael A. Alcorn, et al.

In many multi-agent spatiotemporal systems, the agents are 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.


baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modeling

Multi-agent spatiotemporal modeling is a challenging task from both an a...

Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning

This paper considers multi-agent reinforcement learning (MARL) tasks whe...

Multi-Agent Imitation Learning with Copulas

Multi-agent imitation learning aims to train multiple agents to perform ...

Fine-Grained Retrieval of Sports Plays using Tree-Based Alignment of Trajectories

We propose a novel method for effective retrieval of multi-agent spatiot...

Latent Variable Nested Set Transformers AutoBots

Humans have the innate ability to attend to the most relevant actors in ...

Generative Multi-Agent Behavioral Cloning

We propose and study the problem of generative multi-agent behavioral cl...

Double Deep Q-Learning in Opponent Modeling

Multi-agent systems in which secondary agents with conflicting agendas a...

Code Repositories


A look-ahead multi-entity Transformer for modeling coordinated agents.

view repo