Stephanie Milani

I am a Ph.D. student in the Machine Learning Department at Carnegie Mellon University, where I am advised by Fei Fang. Previously, I interned at Microsoft Research Montreal with Geoff Gordon and in the Microsoft Research Cambridge Deep Reinforcement Learning for Games group with Katja Hofmann. I aim to create intelligent agents that can learn quickly, explain their decisions, and work harmoniously with people and other artificially intelligent agents. I am particularly interested in reinforcement learning.

I completed my B.S. in Computer Science and B.A. in Psychology at the University of Maryland, Baltimore County, where I worked with Marie desJardins, Cynthia Matuszek, Jennifer Wenzel, Christoph Mertz, Katia Sycara, and David Held.

I am open to and excited about collaborating with others. Please email me if you have any questions about a machine learning (or psychology) project, or if you are interested in a research collaboration.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  Twitter

Preprints

Bi-Level Latent Variable Model for Sample-Efficient Multi-Agent Reinforcement Learning
Aravind Venugopal, Stephanie Milani, Fei Fang, Balaraman Ravindran
arXiv preprint, 2023

Refereed Publications

The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks
Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas, Sander Schulhoff, Brandon Houghton, Rohin Shah
NeurIPS Datasets & Benchmarks Track, 2023 (Oral)

Explainable Reinforcement Learning: A Survey and Comparative Review
Stephanie Milani, Nicholay Topin, Manuela Veloso, Fei Fang
ACM CSUR Special Issue on Trustworthy AI, 2023

Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games
Stephanie Milani, Arthur Juliani, Ida Momennejad, Raluca Georgescu, Jaroslaw Rzpecki, Alison Shaw, Gavin Costello, Fei Fang, Sam Devlin, Katja Hofmann
CHI, 2023
Previous versions in NeurIPS-21 Workshop on Human-Centered AI and CHI-22 Late Breaking Work

Interpretable Multi-Agent Reinforcement Learning with Decision-Tree Policies
Stephanie Milani, Zhicheng Zhang, Nicholay Topin, Zheyuan Ryan Shi, Charles Kamhoua, Evangelos E. Papalexakis, Fei Fang
Explainable Agency in Artificial Intelligence (invited, in submission), 2023

Uni[MASK]: Unified Inference in Sequential Decision Problems
Micah Carroll, Jessy Lin, Orr Paradise, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew Hausknecht, Anca Dragan, Sam Devlin
NeurIPS, 2022 (Oral)
Previous version in ICLR-22 Workshop on Generalizable Policy Learning in the Physical World

MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learning
Stephanie Milani*, Zhicheng Zhang*, Nicholay Topin, Zheyuan Ryan Shi, Charles Kamhoua, Evangelos E. Papalexakis, Fei Fang
ECML-PKDD, 2022
Previous version in AAAI-22 Explainable Agency in AI Workshop

Learning to Play Adaptive Cyber Deception Game
Yinuo Du, Zimeng Song, Stephanie Milani, Coty Gonzalez, Fei Fang
AAMAS OptLearnMAS Workshop, 2022

The MineRL BASALT Competition on Fine-tuning from Human Feedback
Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas, Byron V. Galbraith, Steven H. Wang, Brandon Houghton, Sharada Mohanty, Rohin Shah
NeurIPS Competition Track, 2022

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned
Anssi Kanervisto*, Stephanie Milani*, Karolis Ramanauskas, Nicholay Topin, Zichuan Lin, Junyuo Li, Deheng Ye, Qiang Fu, Wei Yang, Weijun Hong, Zhongyue Huang, Haicheng Chen, Guangjun Zeng, Yue Lin, Vincent Micheli, Eloi Alonso, Francois Fleuret, Alexander Nikulin, Yury Belousov, Oleg Svidchenko, Aleksei Shpilman
PMLR: NeurIPS 2021 Competition and Demonstration Track, 2022

Retrospective on the 2021 MineRL BASALT Competition on Learning from Human Feedback
Rohin Shah, Steven H. Wang, Cody Wild, Stephanie Milani, Anssi Kanervisto, Vinicius G. Goecks, Nicholas Waytowich, David Watkins-Valls, Bharat Prakash, Edmund Mills, Divyansh Garg, Alexander Fries, Alexandra Souly, Chan Jun Shern, Daniel del Castillo, Tom Lieberum
PMLR: NeurIPS 2021 Competition and Demonstration Track, 2022

The MineRL Diamond Competition on Sample Efficient Reinforcement Learning
William H. Guss, Alara Dirik*, Byron Galbraith*, Brandon Houghton*, Anssi Kanervisto*, Noboru Sean Kuno, Stephanie Milani*, Sharada Mohanty*, Karolis Ramanauskas*, Ruslan Salakhutdinov*, Rohin Shah*, Nicholay Topin*, Steven H. Wang*, Cody Wild*
NeurIPS Competition Track, 2021

The MineRL BASALT Competition on Learning from Human Feedback
Rohin Shah, Cody Wild, Steven H. Wang, Neel Alex, Brandon Houghton, William H. Guss, Stephanie Milani, Nicholay Topin, Pieter Abbeel, Stuart Russell, Anca Dragan
NeurIPS Competition Track, 2021

Towards Robust and Domain Agnostic Reinforcement Learning Competitions
William H. Guss, Stephanie Milani, Nicholay Topin, Brandon Houghton, Sharada Mohanty, Andrew Melnik, Augustin Harter, Benoit Buschmaas, Bjarne Jaster, Christoph Berganski, Dennis Heitkamp, Marko Henning, Helge Ritter, Chengjie Wu, Xiaotian Hao, Yiming Lu, Hangyu Mao, Yihuan Mao, Chao Wang, Michal Opanowicz, Anssi Kanervisto, Yanick Schraner, Christian Scheller, Xiren Zhou, Lu Liu, Daichi Nishio, Toi Tsuneda, Karolis Ramanauskas, Gabija Juceviciute
Proceedings of the NeurIPS 2020 Competition & Demonstration Track, 2021

Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods
Nicholay Topin, Stephanie Milani, Fei Fang, Manuela Veloso
AAAI, 2021
bibtex

Harnessing the Power of Deception in Attack Graph-Based Security Games
Stephanie Milani, Weiran Shen, Kevin S. Chan, Sridhar Venkatesan, Nandi O. Leslie, Charles Kamhoua, Fei Fang
GameSec, 2020
bibtex

A Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learning Using Human Priors
Stephanie Milani, Nicholay Topin, Brandon Houghton, William H. Guss, Sharada Mohanty, Keisuke Nakata, Oriol Vinyals, Noboru Sean Kuno
Proceedings of the NeurIPS 2019 Competition & Demonstration Track, 2020
bibtex

NeurIPS2020 Competition: The MineRL Competition on Sample Efficient Reinforcement Learning using Human Priors
William H. Guss, Mario Ynocente Castro*, Sam Devlin*, Brandon Houghton*, Noboru Sean Kuno*, Crissman Loomis*, Stephanie Milani*, Sharada Mohanty*, Keisuke Nakata*, Ruslan Salakhutdinov*, John Schulman*, Shinya Shiroshita*, Nicholay Topin*, Avinash Ummadisingu*, Oriol Vinyals*
NeurIPS Competition Track, 2020
bibtex

Planning with Abstract, Learned Models While Learning Transferable Subtasks
John Winder, Stephanie Milani, Matthew Landen, Erebus Oh, Shane Parr, Shawn Squire, Marie desJardins, Cynthia Matuszek
AAAI, 2020
Previous versions in ICAPS-17 IntEx Workshop, RLDM-17, and Do Good Robotics Symposium 2019
bibtex

Intelligent Tutoring Strategies for Students with Autism Spectrum Disorder: A Reinforcement Learning Approach
Stephanie Milani*, Zhou Fan*, Saurabh Gulati, Thanh Nguyen, Fei Fang, Amulya Yadav
AAAI Workshop on AI for Education, 2020
bibtex

The MineRL Competition on Sample Efficient Reinforcement Learning using Human Priors
William H. Guss, Cayden Codel*, Katja Hofmann*, Brandon Houghton*, Noboru Sean Kuno*, Stephanie Milani*, Sharada Mohanty*, Diego Perez-Liebana*, Ruslan Salakhutdinov*, Nicholay Topin*, Manuela Veloso*, Phillip Wang*
NeurIPS Competition Track, 2019
bibtex

Guaranteeing Reproducibility in Deep Learning Competitions
Brandon Houghton, Stephanie Milani, Nicholay Topin, William H. Guss, Katja Hofmann, Diego Perez-Liebana, Manuela Veloso, Ruslan Salakhutdinov
NeurIPS CiML Workshop, 2019
bibtex

Penalty-Modified Markov Decision Processes: Efficient Incorporation of Norms into Sequential Decision Making Problems
Stephanie Milani, Nicholay Topin, Katia Sycara
RLDM, 2019
bibtex

Perceptions of Domestic Robots' Normative Behavior Across Cultures
Huao Li, Stephanie Milani, Vigneshram Krishnamoorthy, Michael Lewis, Katia Sycara
AI, Ethics, and Society, 2019
bibtex


I got this great website here.