David Abel

Portrait


Conference Papers

Three Dogmas of Reinforcement Learning. BibTex
David Abel, Mark K. Ho, Anna Harutyunyan
RLC 2024.

Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Feedback. BibTex
Andi Peng, Yuying Sun, Tianmin Shu, David Abel
ICML 2024.

A Definition of Continual Reinforcement Learning. BibTex
David Abel, André Barreto, Benjamin Van Roy, Doina Precup, Hado van Hasselt, Satinder Singh.
NeurIPS 2023.

Settling the Reward Hypothesis. BibTex
Michael Bowling, John D. Martin, David Abel, Will Dabney.
ICML 2023.

Meta-Gradients in Non-Stationary Environments. BibTex
Jelena Luketina, Sebastian Flennerhag, Yannick Schroecker, David Abel, Tom Zahavy, Satinder Singh.
CoLLAs 2022.

On the Expressivity of Markov Reward. BibTex
David Abel, Will Dabney, Anna Harutyunyan, Mark K. Ho, Michael L. Littman, Doina Precup, Satinder Singh.
NeurIPS 2021 (Outstanding Paper Award).

Revisiting Peng’s Q(λ) for Modern Reinforcement Learning. BibTex
Tadashi Kozuno, Yunhao Tang, Mark Rowland, Rémi Munos, Steven Kapturowski, Will Dabney, Michal Valko, David Abel.
ICML 2021.

Lipschitz Lifelong Reinforcement Learning. BibTex
Erwan Lecarpentier, David Abel, Kavosh Asadi, Yuu Jinnai, Emmanuel Rachelson, Michael L. Littman.
AAAI 2021. (Earlier version on arXiv)

What can I do here? A Theory of Affordances in Reinforcement Learning. BibTex
Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici, David Abel, Doina Precup.
ICML 2020.

Value Preserving State-Action Abstractions. BibTex
David Abel, Nathan Umbanhowar, Khimya Khetarpal, Dilip Arumugam, Doina Precup, Michael L. Littman.
AISTATS 2020. (Early version from ICLR 2019 workshop).

The Efficiency of Human Cognition Reflects Planned Use of Information Processing. BibTex
Mark K. Ho, David Abel, Jonathan D. Cohen, Michael L. Littman, Thomas L. Griffiths.
AAAI 2020.

The Expected-Length Model of Options. BibTex
David Abel*, John Winder*, Marie desJardins, Michael L. Littman.
IJCAI 2019.

Finding Options that Minimize Planning Time. BibTex
Yuu Jinnai, David Abel, D Ellis Hershkowitz, Michael L. Littman, George Konidaris.
ICML 2019.

Discovering Options for Exploration by Minimizing Cover Time. BibTex
Yuu Jinnai, Jee Won Park, David Abel, George Konidaris.
ICML 2019.

State Abstraction as Compression in Apprenticeship Learning. BibTex
David Abel, Dilip Arumugam, Kavosh Asadi, Yuu Jinnai, Michael L. Littman, Lawson L.S. Wong.
AAAI 2019.

State Abstractions for Lifelong Reinforcement Learning. BibTex
David Abel, Dilip Arumugam, Lucas Lehnert, Michael L. Littman.
ICML 2018.

Policy and Value Transfer in Lifelong Reinforcement Learning. BibTex
David Abel*, Yuu Jinnai*, Yue Guo, George Konidaris, Michael L. Littman.
ICML 2018.

Bandit-Based Solar Panel Control. BibTex
David Abel, Edward C. Williams, Stephen Brawner, Emily Reif, Michael L. Littman.
IAAI 2018. (Early versions from RLDM 2017 and EnviroInfo 2017).

Near Optimal Behavior via Approximate State Abstraction. BibTex
David Abel*, D Ellis Hershkowitz*, Michael L. Littman.
ICML 2016. (Extended version on arXiv).

Goal Based Action Priors. BibTex
David Abel, D Ellis Hershkowitz, Gabriel Barth-Maron, Stephen Brawner, Kevin O'Farrell, James MacGlashan, Stefanie Tellex.
ICAPS 2015.

Journal Papers

People construct simplified mental representations to plan. BibTex
Mark K. Ho, David Abel, Carlos G. Correa, Michael L. Littman, Jonathan D. Cohen, Thomas L. Griffiths.
Nature, 2022.

The Value of Abstraction. BibTex
Mark K. Ho, David Abel, Thomas L. Griffiths, Michael L. Littman.
Current Opinions in Behavioral Sciences, 2019.

Theses

A Theory of Abstraction in Reinforcement Learning. BibTex (original)
David Abel. Advised by Prof. Michael Littman.
Ph.D Thesis (Computer Science), Brown University, 2020.

Concepts in Bounded Rationality: Perspectives from Reinforcement Learning. BibTex
David Abel. Advised by Prof. Joshua Schechter.
Master’s Thesis (Philosophy), Brown University, 2019.

Learning to Plan in Complex Stochastic Domains. BibTex
David Abel. Advised by Prof. Stefanie Tellex.
Master’s Thesis (Computer Science), Brown University, 2015.

Toward the Defense of Hypercomputation. (Revised Version Coming Eventually)
David Abel. Co-advised by Prof. Anna Moltchanova and Prof. Jason Decker.
Bachelor’s Thesis (Philosophy), Carleton College, 2013.

Workshops, Symposia, and Extended Abstracts

Expressing Non-Markov Reward to a Markov Agent. BibTex
David Abel, André Barreto, Michael Bowling, Will Dabney, Steven Hansen, Anna Harutyunyan, Mark K. Ho, Ramana Kumar, Michael L. Littman, Doina Precup, Satinder Singh.
RLDM 2022.

Meta-Gradients in Non-Stationary Environments. BibTex
Jelena Luketina, Sebastian Flennerhag, Yannick Schroecker, David Abel, Tom Zahavy, Satinder Singh.
ICLR Workshop on Agent Learning in Open-Endedness, 2022.

On the Expressivity of Markov Reward (Extended Abstract). BibTex
David Abel, Will Dabney, Anna Harutyunyan, Mark K. Ho, Michael L. Littman, Doina Precup, Satinder Singh.
IJCAI (Sister Conferences Best Papers Track), 2022.

Bad-Policy Density: A Measure of Reinforcement Learning Hardness. BibTex
David Abel, Cameron Allen, Dilip Arumugam, D. Ellis Hershkowitz, Michael L. Littman, Lawson L.S. Wong.
ICML Workshop on Reinforcement Learning Theory, 2021.

Skill Discovery with Well-Defined Objectives. BibTex
Yuu Jinnai, David Abel, Jee Won Park, D Ellis Hershkowitz, Michael L. Littman, George Konidaris.
ICLR Workshop on Structure and Priors in RL, 2019.

simple_rl: Reproducible Reinforcement Learning in Python. BibTex
David Abel.
ICLR Workshop on Reproducibility in Machine Learning, 2019.

A Theory of State Abstraction for Reinforcement Learning. BibTex
David Abel.
AAAI Doctoral Consortium, 2019.

Toward Good Abstractions for Lifelong Learning. BibTex
David Abel, Dilip Arumugam, Lucas Lehnert, Michael L. Littman.
NeurIPS Workshop on Hierarchical Reinforcement Learning, 2017.

Agent-Agnostic Human-In-The-Loop Reinforcement Learning. BibTex
David Abel, John Salvatier, Andreas Stuhlmüller, Owain Evans.
NeurIPS Workshop on the Future of Interactive Learning Machines, 2016.

Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains. BibTex
David Abel, Alekh Agarwal, Fernando Diaz, Akshay Krishnamurthy, Robert Schapire.
ICML Workshop on Abstraction in Reinforcement Learning, 2016.

Reinforcement Learning as a Framework for Ethical Decision Making. BibTex
David Abel, James MacGlashan, Michael L. Littman.
AAAI Workshop on AI, Ethics, and Society, 2016.

Affordances as Transferrable Knowledge for Planning Agents. BibTex
Gabriel Barth-Maron, David Abel, James MacGlashan, Stefanie Tellex.
AAAI Symposium on Knowledge and Skill Transfer, 2014.

Toward Affordance-Aware Planning. BibTex
David Abel, Gabriel Barth-Maron, James MacGlashan, Stefanie Tellex.
RSS Workshop on Affordances in Vision for Cognitive Robotics, 2014.

Preprints

A Hypothesis on Black Swan in Unchanging Environments. BibTex
Hyunin Lee, Chanwoo Park, David Abel, Ming Jin.
Preprint, 2024.

On the Convergence of Bounded Agents. BibTex
David Abel, André Barreto, Hado van Hasselt, Benjamin Van Roy, Doina Precup, Satinder Singh.
Preprint, 2023.

Control of Mental Representations in Human Planning. BibTex
Mark K. Ho, David Abel, Carlos G. Correa, Michael L. Littman, Jonathan D. Cohen, Thomas L. Griffiths.
Preprint, 2021.

Learning State Abstractions for Transfer in Continuous Control. BibTex
Kavosh Asadi, David Abel, Michael L. Littman.
Preprint, 2020.

Mitigating Planner Overfitting in Model-Based Reinforcement Learning. BibTex
Dilip Arumugam, David Abel, Kavosh Asadi, Nakul Gopalan, Christopher Grimm, Jun Ki Lee, Lucas Lehnert, Michael L. Littman.
Preprint, 2018.

Modeling Latent Attention Within Neural Networks. BibTex
Christopher Grimm, Dilip Arumugam, Siddharth Karamcheti, David Abel, Lawson L.S. Wong, Michael L. Littman.
Preprint, 2017.