Lars Lien Ankile

44 Vassar St

Cambridge, MA 02139

I’m an M.Eng. of Data Science student at Harvard University, currently working on my thesis at MIT CSAIL in Prof. Pulkit Agrawal’s Improbable AI group, where I’m currently investigating learning-based methods for robotic manipulation.

Before this, I spent a year in the Data to Actionable Knowledge Lab at Harvard, working with Profs. Weiwei Pan and Finale Doshi-Velez on applying RL and Bayesian inference to model human decision-making for frictionful tasks in healthcare settings. I also worked with Prof. David Parkes and Matheus Ferreira in the EconCS Lab at Harvard working on detecting manipulation in multi-agent settings.

I did my undergrad at the Norwegian University of Science and Technology (NTNU) and did my thesis work on applying Deep RL to econometric forecasting of complex and multivariate time series, supervised by Prof. Sjur Westgaard.

Research Interests

My research goal is to enable machines to learn in a human-like manner, primarily through observation and interaction by developing methods merging imitation and reinforcement learning with robust policy representations. I aim to bridge the current divide between general policies that address simple tasks and more specialized policies tailored for complex tasks.

Here’s a sneek peek into our ongoing project on making capable behavior model for furniture assembly tasks:

Furniture Assembly

news

Apr 10, 2024	Our recent work on Data-Efficient Imitation Learning for Robotic Assembly is available to read on arXiv! In this work, we show how one can learn long assemblies (~2500 timesteps) with only <50 demonstrations using diffusion policies and data augmentation strategies.

selected publications

arXiv

JUICER: Data-Efficient Imitation Learning for Robotic Assembly

Lars Ankile, Anthony Simeonov, Idan Shenfeld, and 1 more author

2024

Abs HTML PDF Code

While learning from demonstrations is powerful for acquiring visuomotor policies, high-performance imitation without large demonstration datasets remains challenging for tasks requiring precise, long-horizon manipulation. This paper proposes a pipeline for improving imitation learning performance with a small human demonstration budget. We apply our approach to assembly tasks that require precisely grasping, reorienting, and inserting multiple parts over long horizons and multiple task phases. Our pipeline combines expressive policy architectures and various techniques for dataset expansion and simulation-based data augmentation. These help expand dataset support and supervise the model with locally corrective actions near bottleneck regions requiring high precision. We demonstrate our pipeline on four furniture assembly tasks in simulation, enabling a manipulator to assemble up to five parts over nearly 2500 time steps directly from RGB images, outperforming imitation and data augmentation baselines.
I See You! Robust Measurement of Adversarial Behavior

Lars Ankile, Matheus XV Ferreira, and David Parkes

In Multi-Agent Security Workshop @ NeurIPS’23 2023

Abs PDF Code

We introduce the study of non-manipulable measures of manipulative behavior in multi-agent systems. We do this through a case study of decentralized finance (DeFi) and blockchain systems, which are salient as real-world, rapidly emerging multi-agent systems with financial incentives for malicious behavior, for the participation in algorithmic and AI systems, and in highlighting the need for new methods with which to measure levels of manipulative behavior. We introduce a new surveillance metric for measuring malicious behavior in this context and demonstrate its effectiveness in a natural experiment to the Uniswap DeFi ecosystem.
Discovering User Types: Mapping User Traits by Task-Specific Behaviors in Reinforcement Learning

Lars Lien Ankile, Brian Ham, Kevin Mao, and 4 more authors

In First Workshop on Theory of Mind in Communicating Agents @ ICML’23 2023

Abs PDF Code

When assisting human users in reinforcement learning (RL), we can represent users as RL agents and study key parameters, called user traits, to inform intervention design. We study the relationship between user behaviors (policy classes) and user traits. Given an environment, we introduce an intuitive tool for studying the breakdown of "user types": broad sets of traits that result in the same behavior. We show that seemingly different real-world environments admit the same set of user types and formalize this observation as an equivalence relation defined on environments. By transferring intervention design between environments within the same equivalence class, we can help rapidly personalize interventions.
M.Sc.

Exploration of Forecasting Paradigms and a Generalized Forecasting Framework

Lars Lien Ankile, and Kjartan Krange

2022

Abs HTML PDF Code

First, this paper presents a total ordering of the theoretical lower bound loss of different forecasting paradigms in the following descending order: Model selection, Model combination, Non-parametric univariate models, and Non-parametric multivariate models. Second, we create a generalized forecasting framework to test the above forecasting paradigms ex-ante. We implement the framework by creating a novel datacube consisting of daily stock prices and 100,000 quarterly reports from about 1600 global companies and several daily macro time series, all from 2000 to spring 2022. Lastly, we utilize the framework and show that modern multivariate time series approaches are powerful but domain-dependent. We demonstrate the domain-dependent accuracy by showing convincing results when predicting corporate bankruptcy risk, moderate results when predicting stock price volatility, and lacking results when finally predicting company market capitalization. Given the domain-dependent convincing results and mostly unrealized theoretical lower bound loss of multivariate approaches, we hope to encourage further research on non-parametric, multi-signal approaches that leverage a wider array of available information.