“Baller2vec++: A Look-Ahead Multi-Entity Transformer For Modeling Coordinated Agents”, Michael A. Alcorn, Anh Nguyen2021-04-24 (Decision Transformer, MARL; similar)⁠:

[cf. Decision Transformer] In many multi-agent spatiotemporal systems, agents operate under the influence of shared, unobserved variables (eg. 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. [Github]

Similar Links: