Brennan Shacklett

Brennan Shacklett

Auto-generated profile, based on publicly available information

Brennan Shacklett

Stanford University

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 July 2023 in ACM Transactions on Graphics
Verified
Journal Article
Open access
BSBrennan Shacklett
Brennan Shacklett
LRLuc Guy Rosenzweig
Luc Guy Rosenzweig
ZXZhiqiang Xie
Zhiqiang Xie
BSBidipta Sarkar
Bidipta Sarkar
ASAndrew Szot
Andrew Szot
KFKayvon Fatahalian
Kayvon Fatahalian
Training AI agents to perform complex tasks in simulated worlds requires millions to billions of steps of experience. To achieve high performance, today's fastest simulators for training AI agents adopt the idea of batch simulation: using a single simulation engine to simultaneously step many environments in parallel. We introduce a framework for productively authoring novel training environments (including custom logic for environment generation, environment time stepping, and generating agent observations and rewards) that execute as high-performance, GPU-accelerated batched simulators. Our key observation is that the entity-component-system (ECS) design pattern, popular for expressing CPU-side game logic today, is also well-suited for providing the structure needed for high-performance batched simulators. We contribute the first fully-GPU accelerated ECS implementation that natively supports batch environment simulation. We demonstrate how ECS abstractions impose structure on a training environment's logic and state that allows the system to efficiently manage state, amortize work, and identify GPU-friendly coherent parallel computations within and across different environments. We implement several learning environments in this framework, and demonstrate GPU speedups of two to three orders of magnitude over open source CPU baselines and 5-33× over strong baselines running on a 32-thread CPU. An implementation of the OpenAI hide and seek 3D environment written in our framework, which performs rigid body physics and ray tracing in each simulator step, achieves over 1.9 million environment steps per second on a single GPU.

9 October 2024 in Computer Graphics Forum
Verified
Journal Article
Closed access
DDD. Durst
D. Durst
FXF. Xie
F. Xie
VSV. Sarukkai
V. Sarukkai
BSB. Shacklett
B. Shacklett
IFI. Frosio
I. Frosio
KFK. Fatahalian
K. Fatahalian

3 December 2024
Verified
Conference Paper
Open access
LRLuc Guy Rosenzweig
Luc Guy Rosenzweig
BSBrennan Shacklett
Brennan Shacklett
WXWarren Xia
Warren Xia
KFKayvon Fatahalian
Kayvon Fatahalian

25 August 2024 in arXiv
Verified
Preprint
Open access
PDF file
DDDavid Durst
David Durst
FXFeng Xie
Feng Xie
VSVishnu Sarukkai
Vishnu Sarukkai
BSBrennan Shacklett
Brennan Shacklett
IFIuri Frosio
Iuri Frosio
KFKayvon Fatahalian
Kayvon Fatahalian
In multiplayer, first-person shooter games like Counter-Strike: Global Offensive (CS:GO), coordinated movement is a critical component of high-level strategic play. However, the complexity of team coordination and the variety of conditions present in popular game maps make it impractical to author hand-crafted movement policies for every scenario. We show that it is possible to take a data-driven approach to creating human-like movement controllers for CS:GO. We curate a team movement dataset comprising 123 hours of professional game play traces, and use this dataset to train a transformer-based movement model that generates human-like team movement for all players in a "Retakes" round of the game. Importantly, the movement prediction model is efficient. Performing inference for all players takes less than 0.5 ms per game step (amortized cost) on a single CPU core, making it plausible for use in commercial games today. Human evaluators assess that our model behaves more like humans than both commercially-available bots and procedural movement controllers scripted by experts (16% to 59% higher by TrueSkill rating of "human-like"). Using experiments involving in-game bot vs. bot self-play, we demonstrate that our model performs simple forms of teamwork, makes fewer common movement mistakes, and yields movement distributions, player lifetimes, and kill locations similar to those observed in professional CS:GO match play.