Philip S. Thomas

According to our database, Philip S. Thomas authored at least 75 papers between 2009 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

ICU-Sepsis: A Benchmark MDP Built from Real Medical Data.

Kartik Choudhary, Dhawal Gupta, Philip S. Thomas

CoRR, 2024

Position: Benchmarking is Limited in Reinforcement Learning Research.

Scott M. Jordan, Adam White, Bruno Castro da Silva, Martha White, Philip S. Thomas

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Analyzing the Relationship Between Difference and Ratio-Based Fairness Metrics.

Min-Hsuan Yeh, Blossom Metevier, Austin Hoag, Philip S. Thomas

Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency, 2024

From Past to Future: Rethinking Eligibility Traces.

Dhawal Gupta, Scott M. Jordan, Shreyas Chaudhari, Bo Liu, Philip S. Thomas, Bruno Castro da Silva

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Learning Fair Representations with High-Confidence Guarantees.

Yuhong Luo, Austin Hoag, Philip S. Thomas

CoRR, 2023

Coagent Networks: Generalized and Scaled.

James E. Kostas, Scott M. Jordan, Yash Chandak, Georgios Theocharous, Dhawal Gupta, Martha White, Bruno Castro da Silva, Philip S. Thomas

CoRR, 2023

Optimization using Parallel Gradient Evaluations on Multiple Parameters.

Yash Chandak, Shiv Shankar, Venkata Gandikota, Philip S. Thomas, Arya Mazumdar

CoRR, 2023

Behavior Alignment via Reward Function Optimization.

Dhawal Gupta, Yash Chandak, Scott M. Jordan, Philip S. Thomas, Bruno C. da Silva

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Seldonian Toolkit: Building Software with Safe and Fair Machine Learning.

Austin Hoag, James E. Kostas, Bruno Castro da Silva, Philip S. Thomas, Yuriy Brun

Proceedings of the 45th IEEE/ACM International Conference on Software Engineering: ICSE 2023 Companion Proceedings, 2023

Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments.

Vincent Liu, Yash Chandak, Philip S. Thomas, Martha White

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Enforcing Delayed-Impact Fairness Guarantees.

Aline Weber, Blossom Metevier, Yuriy Brun, Philip S. Thomas, Bruno Castro da Silva

CoRR, 2022

Adaptive Rollout Length for Model-Based RL Using Model-Free Deep RL.

Abhinav Bhatia, Philip S. Thomas, Shlomo Zilberstein

CoRR, 2022

Off-Policy Evaluation for Action-Dependent Non-stationary Environments.

Yash Chandak, Shiv Shankar, Nathaniel D. Bastian, Bruno C. da Silva, Emma Brunskill, Philip S. Thomas

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Mechanizing Soundness of Off-Policy Evaluation.

Jared Yeager, J. Eliot B. Moss, Michael Norrish, Philip S. Thomas

Proceedings of the 13th International Conference on Interactive Theorem Proving, 2022

Fairness Guarantees under Demographic Shift.

Stephen Giguere, Blossom Metevier, Bruno Castro da Silva, Yuriy Brun, Philip S. Thomas, Scott Niekum

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Edge-Compatible Reinforcement Learning for Recommendations.

James E. Kostas, Philip S. Thomas, Georgios Theocharous

CoRR, 2021

Large-scale Interactive Conversational Recommendation System using Actor-Critic Framework.

Ali Montazeralghaem, James Allan, Philip S. Thomas

Proceedings of the RecSys '21: Fifteenth ACM Conference on Recommender Systems, Amsterdam, The Netherlands, 27 September 2021, 2021

SOPE: Spectrum of Off-Policy Estimators.

Christina J. Yuan, Yash Chandak, Stephen Giguere, Philip S. Thomas, Scott Niekum

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs.

Harsh Satija, Philip S. Thomas, Joelle Pineau, Romain Laroche

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Structural Credit Assignment in Neural Networks using Reinforcement Learning.

Dhawal Gupta, Gabor Mihucz, Matthew Schlegel, James E. Kostas, Philip S. Thomas, Martha White

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Universal Off-Policy Evaluation.

Yash Chandak, Scott Niekum, Bruno C. da Silva, Erik G. Learned-Miller, Emma Brunskill, Philip S. Thomas

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Towards Practical Mean Bounds for Small Samples.

My Phan, Philip S. Thomas, Erik G. Learned-Miller

Proceedings of the 38th International Conference on Machine Learning, 2021

Posterior Value Functions: Hindsight Baselines for Policy Gradient Methods.

Chris Nota, Philip S. Thomas, Bruno C. da Silva

Proceedings of the 38th International Conference on Machine Learning, 2021

High Confidence Generalization for Reinforcement Learning.

James E. Kostas, Yash Chandak, Scott M. Jordan, Georgios Theocharous, Philip S. Thomas

Proceedings of the 38th International Conference on Machine Learning, 2021

High-Confidence Off-Policy (or Counterfactual) Variance Estimation.

Yash Chandak, Shiv Shankar, Philip S. Thomas

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Reinforcement Learning for Strategic Recommendations.

Georgios Theocharous, Yash Chandak, Philip S. Thomas, Frits de Nijs

CoRR, 2020

Learning Reusable Options for Multi-Task Reinforcement Learning.

Francisco M. Garcia, Chris Nota, Philip S. Thomas

CoRR, 2020

Security Analysis of Safe and Seldonian Reinforcement Learning Algorithms.

Pinar Ozisik, Philip S. Thomas

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Towards Safe Policy Improvement for Non-Stationary MDPs.

Yash Chandak, Scott M. Jordan, Georgios Theocharous, Martha White, Philip S. Thomas

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Asynchronous Coagent Networks.

James E. Kostas, Chris Nota, Philip S. Thomas

Proceedings of the 37th International Conference on Machine Learning, 2020

Evaluating the Performance of Reinforcement Learning Algorithms.

Scott M. Jordan, Yash Chandak, Daniel Cohen, Mengxue Zhang, Philip S. Thomas

Proceedings of the 37th International Conference on Machine Learning, 2020

Optimizing for the Future in Non-Stationary MDPs.

Yash Chandak, Georgios Theocharous, Shiv Shankar, Martha White, Sridhar Mahadevan, Philip S. Thomas

Proceedings of the 37th International Conference on Machine Learning, 2020

Is the Policy Gradient a Gradient?

Chris Nota, Philip S. Thomas

Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems, 2020

Lifelong Learning with a Changing Action Set.

Yash Chandak, Georgios Theocharous, Chris Nota, Philip S. Thomas

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

Reinforcement Learning When All Actions Are Not Always Available.

Yash Chandak, Georgios Theocharous, Blossom Metevier, Philip S. Thomas

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019

Reinforcement learning with spiking coagents.

Sneha Aenugu, Abhishek Sharma, Sasikiran Yelamarthi, Hananel Hazan, Philip S. Thomas, Robert Kozma

CoRR, 2019

Classical Policy Gradient: Preserving Bellman's Principle of Optimality.

Philip S. Thomas, Scott M. Jordan, Yash Chandak, Chris Nota, James E. Kostas

CoRR, 2019

A New Confidence Interval for the Mean of a Bounded Random Variable.

Erik G. Learned-Miller, Philip S. Thomas

CoRR, 2019

Asynchronous Coagent Networks: Stochastic Networks for Reinforcement Learning without Backpropagation or a Clock.

James E. Kostas, Chris Nota, Philip S. Thomas

CoRR, 2019

Privacy Preserving Off-Policy Evaluation.

Tengyang Xie, Philip S. Thomas, Gerome Miklau

CoRR, 2019

Offline Contextual Bandits with High Probability Fairness Guarantees.

Blossom Metevier, Stephen Giguere, Sarah Brockman, Ari Kobren, Yuriy Brun, Emma Brunskill, Philip S. Thomas

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning.

Francisco M. Garcia, Philip S. Thomas

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Concentration Inequalities for Conditional Value at Risk.

Philip S. Thomas, Erik G. Learned-Miller

Proceedings of the 36th International Conference on Machine Learning, 2019

Learning Action Representations for Reinforcement Learning.

Yash Chandak, Georgios Theocharous, James E. Kostas, Scott M. Jordan, Philip S. Thomas

Proceedings of the 36th International Conference on Machine Learning, 2019

A Compression-Inspired Framework for Macro Discovery.

Francisco M. Garcia, Bruno C. da Silva, Philip S. Thomas

Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, 2019

Natural Option Critic.

Saket Tiwari, Philip S. Thomas

Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

2018

Importance Sampling for Fair Policy Selection.

Shayan Doroudi, Philip S. Thomas, Emma Brunskill

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018

Decoupling Gradient-Like Learning Rules from Representations.

Philip S. Thomas, Christoph Dann, Emma Brunskill

Proceedings of the 35th International Conference on Machine Learning, 2018

2017

On Ensuring that Intelligent Machines Are Well-Behaved.

Philip S. Thomas, Bruno Castro da Silva, Andrew G. Barto, Emma Brunskill

CoRR, 2017

Decoupling Learning Rules from Representations.

Philip S. Thomas, Christoph Dann, Emma Brunskill

CoRR, 2017

Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines.

Philip S. Thomas, Emma Brunskill

CoRR, 2017

Using Options for Long-Horizon Off-Policy Evaluation.

Zhaohan Daniel Guo, Philip S. Thomas, Emma Brunskill

CoRR, 2017

Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation.

Zhaohan Guo, Philip S. Thomas, Emma Brunskill

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Data-Efficient Policy Evaluation Through Behavior Policy Search.

Josiah P. Hanna, Philip S. Thomas, Peter Stone, Scott Niekum

Proceedings of the 34th International Conference on Machine Learning, 2017

Predictive Off-Policy Policy Evaluation for Nonstationary Decision Problems, with Applications to Digital Marketing.

Philip S. Thomas, Georgios Theocharous, Mohammad Ghavamzadeh, Ishan Durugkar, Emma Brunskill

Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

Importance Sampling with Unequal Support.

Philip S. Thomas, Emma Brunskill

Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

2016

Human-Like Rewards to Train a Reinforcement Learning Controller for Planar Arm Movement.

Kathleen M. Jagodnik, Philip S. Thomas, Antonie J. van den Bogert, Michael S. Branicky, Robert F. Kirsch

IEEE Trans. Hum. Mach. Syst., 2016

Energetic Natural Gradient Descent.

Philip S. Thomas, Bruno Castro da Silva, Christoph Dann, Emma Brunskill

Proceedings of the 33nd International Conference on Machine Learning, 2016

Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning.

Philip S. Thomas, Emma Brunskill

Proceedings of the 33nd International Conference on Machine Learning, 2016

Increasing the Action Gap: New Operators for Reinforcement Learning.

Marc G. Bellemare, Georg Ostrovski, Arthur Guez, Philip S. Thomas, Rémi Munos

Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016

2015

A Notation for Markov Decision Processes.

Philip S. Thomas

CoRR, 2015

Ad Recommendation Systems for Life-Time Value Optimization.

Georgios Theocharous, Philip S. Thomas, Mohammad Ghavamzadeh

Proceedings of the 24th International Conference on World Wide Web Companion, 2015

Policy Evaluation Using the Ω-Return.

Philip S. Thomas, Scott Niekum, Georgios Theocharous, George Dimitri Konidaris

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Personalized Ad Recommendation Systems for Life-Time Value Optimization with Guarantees.

Georgios Theocharous, Philip S. Thomas, Mohammad Ghavamzadeh

Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, 2015

High Confidence Policy Improvement.

Philip S. Thomas, Georgios Theocharous, Mohammad Ghavamzadeh

Proceedings of the 32nd International Conference on Machine Learning, 2015

High-Confidence Off-Policy Evaluation.

Philip S. Thomas, Georgios Theocharous, Mohammad Ghavamzadeh

Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015

2014

Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces.

Sridhar Mahadevan, Bo Liu, Philip S. Thomas, William Dabney, Stephen Giguere, Nicholas Jacek, Ian Gemp, Ji Liu

CoRR, 2014

Natural Temporal Difference Learning.

William Dabney, Philip S. Thomas

Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, 2014

2013

Projected Natural Actor-Critic.

Philip S. Thomas, William Dabney, Stephen Giguere, Sridhar Mahadevan

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

2012

Motor primitive discovery.

Philip S. Thomas, Andrew G. Barto

Proceedings of the 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics, 2012

2011

Policy Gradient Coagent Networks.

Philip S. Thomas

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

TD_gamma: Re-evaluating Complex Backups in Temporal Difference Learning.

George Dimitri Konidaris, Scott Niekum, Philip S. Thomas

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

Conjugate Markov Decision Processes.

Philip S. Thomas, Andrew G. Barto

Proceedings of the 28th International Conference on Machine Learning, 2011

Value Function Approximation in Reinforcement Learning Using the Fourier Basis.

George Dimitri Konidaris, Sarah Osentoski, Philip S. Thomas

Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, 2011

2009

Application of the Actor-Critic Architecture to Functional Electrical Stimulation Control of a Human Arm.

Philip S. Thomas, Antonie J. van den Bogert, Kathleen M. Jagodnik, Michael S. Branicky

Proceedings of the Twenty-First Conference on Innovative Applications of Artificial Intelligence, 2009