Skip to content
conftrace_

Philip S. Thomas

25 papers · 2011–2024 · 6 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+10 more ↓ πŸ—ΊοΈ Taxonomy Completionist (35) 🌍 Conference Polyglot Β· Silver πŸƒ Academic Marathon Β· Half πŸŒ‰ Interdisciplinary Bridge Β· Bronze 🐣 Hot Topic Early Bird
🌱 Topic Pioneer 🧭 Keyword Pioneer πŸ† Keyword Champion (3) πŸ† Grand Slam πŸ“ˆ Trend Setter πŸš€ Conference Pioneer πŸ—ƒοΈ Keyword Collector (107) πŸ”₯ Unstoppable Β· Bronze πŸ’Ž Century Club Β· Bronze ⚑ Prolific Year Β· Productive

Venues

NeurIPS (16) AAAI (3) ICML (2) IJCAI (2) ICLR (1) JMLR (1)

Top co-authors

Yash Chandak (7) Scott Niekum (7) Emma Brunskill (5) Martha White (4) Bruno Castro da Silva (4) Stephen Giguere (4) Dhawal Gupta (3) Georgios Theocharous (3) Scott Jordan (2) Yuriy Brun (2)

Research topics

Reinforcement Learning (20) Machine Learning (19) Methods (18) Optimization & Theory (13) Learning Types (11) Artificial Intelligence (10) Core AI (9) Application Areas (4) Applications (2) Core Methods (2) Learning Paradigms (1)

Keywords

off-policy evaluation (9) reinforcement learning (6) policy search (3) policy evaluation (3) markov decision process (3) variance estimation (3) temporal difference learning (3) safe policy improvement (2) safe reinforcement learning (2) behavior policy (2) offline reinforcement learning (2) mean squared error (2) importance sampling (2) counterfactual reasoning (2) sequential decision making (2) policy gradient (2) temporal abstraction (2) natural gradient (2) transfer learning (1) policy optimization (1)

Papers

Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation NeurIPS 2024 Data-Efficient Policy Evaluation Through Behavior Policy Search JMLR 2024 From Past to Future: Rethinking Eligibility Traces AAAI 2024 Position: Benchmarking is Limited in Reinforcement Learning Research ICML 2024 Behavior Alignment via Reward Function Optimization NeurIPS 2023 Fairness Guarantees under Demographic Shift ICLR 2022 Off-Policy Evaluation for Action-Dependent Non-stationary Environments NeurIPS 2022 High-Confidence Off-Policy (or Counterfactual) Variance Estimation AAAI 2021 Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs NeurIPS 2021 SOPE: Spectrum of Off-Policy Estimators NeurIPS 2021 Structural Credit Assignment in Neural Networks using Reinforcement Learning NeurIPS 2021 Universal Off-Policy Evaluation NeurIPS 2021 Security Analysis of Safe and Seldonian Reinforcement Learning Algorithms NeurIPS 2020 Towards Safe Policy Improvement for Non-Stationary MDPs NeurIPS 2020 A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning NeurIPS 2019 Natural Option Critic AAAI 2019 Offline Contextual Bandits with High Probability Fairness Guarantees NeurIPS 2019 Importance Sampling for Fair Policy Selection IJCAI 2018 Data-Efficient Policy Evaluation Through Behavior Policy Search ICML 2017 Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation NeurIPS 2017 Personalized Ad Recommendation Systems for Life-Time Value Optimization with Guarantees IJCAI 2015 Policy Evaluation Using the Ξ©-Return NeurIPS 2015 Projected Natural Actor-Critic NeurIPS 2013 Policy Gradient Coagent Networks NeurIPS 2011 TD_gamma: Re-evaluating Complex Backups in Temporal Difference Learning NeurIPS 2011