YC
Yinlam Chow
cs.AIcs.LGstat.MLmath.OCcs.CLcs.SYeess.SYcs.IRcs.ROcs.CV
On Valency
published · living versionsW_d8cbc6rs·v1 · currentpublished
Policy Gradient for Coherent Risk Measures
with Aviv Tamar, Mohammad Ghavamzadeh, Shie Mannor
1 version
W_9cba8n4v·v1published
W_ybywrwg8·v1published
Preprints & journals
55 papers in the corpus · 2014–2026Spectral Souping: A Unified Framework for Online Preference Alignment2605.20408v1 · Yinlam Chow, Guy Tennenholtz, Ted Yun et al.2026 · 0 citationsarXiv
Synthetic Dialogue Generation for Interactive Conversational Elicitation & Recommendation (ICER)2510.02331v1 · Moonkyung Ryu, Chih-Wei Hsu, Yinlam Chow et al.2025 · 0 citationsarXiv
Descriptive History Representations: Learning Representations by Answering Questions2506.02125v1 · Guy Tennenholtz, Jihwan Jeong, Chih-Wei Hsu et al.2025 · 0 citationsarXiv
Gemma 3 Technical Report2503.19786v1 · Gemma Team: Aishwarya Kamath, Johan Ferret, Shreya Pathak et al.2025 · 72 citationsarXiv
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models2412.15287v2 · Yinlam Chow, Guy Tennenholtz, Izzeddin Gur et al.2024 · 1 citationarXiv
Preference Adaptive and Sequential Text-to-Image Generation2412.10419v2 · Ofir Nabati, Guy Tennenholtz, ChihWei Hsu et al.2024 · 0 citationsarXiv
Embedding-Aligned Language Models2406.00024v2 · Guy Tennenholtz, Yinlam Chow, Chih-Wei Hsu et al.2024 · 0 citationsarXiv
DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning2402.15957v2 · Anthony Liang, Guy Tennenholtz, Chih-wei Hsu et al.2024 · 1 citationNeural Information Processing Systems (NeurIPS) 2024
Preference Elicitation with Soft Attributes in Interactive Recommendation2311.02085v1 · Erdem Biyik, Fan Yao, Yinlam Chow et al.2023 · 0 citationsarXiv
Factual and Personalized Recommendations using Language Models and Reinforcement Learning2310.06176v1 · Jihwan Jeong, Yinlam Chow, Guy Tennenholtz et al.2023 · 0 citationsarXiv
Demystifying Embedding Spaces using Large Language Models2310.04475v2 · Guy Tennenholtz, Yinlam Chow, Chih-Wei Hsu et al.2023 · 5 citationsarXiv
Offline Reinforcement Learning for Mixture-of-Expert Dialogue Management2302.10850v2 · Dhawal Gupta, Yinlam Chow, Aza Tulepbergenov et al.2023 · 2 citationsarXiv
Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning2208.02294v1 · Deborah Cohen, Moonkyung Ryu, Yinlam Chow et al.2022 · 8 citationsarXiv
A Mixture-of-Expert Approach to RL-based Dialogue Management2206.00059v1 · Yinlam Chow, Aza Tulepbergenov, Ofir Nachum et al.2022 · 3 citationsarXiv
Efficient Risk-Averse Reinforcement Learning2205.05138v2 · Ido Greenberg, Yinlam Chow, Mohammad Ghavamzadeh et al.2022 · 15 citationsarXiv
SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition2202.04849v2 · Dylan Slack, Yinlam Chow, Bo Dai et al.2022 · 3 citationsarXiv
Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors2202.02830v3 · Christina Gopfert, Alex Haig, Yinlam Chow et al.2022 · 4 citationsarXiv
Non-Stationary Latent Bandits2012.00386v1 · Joey Hong, Branislav Kveton, Manzil Zaheer et al.2020 · 3 citationsarXiv
CoinDICE: Off-Policy Confidence Interval Estimation2010.11652v1 · Bo Dai, Ofir Nachum, Yinlam Chow et al.2020 · 18 citationsarXiv
Safe Reinforcement Learning with Natural Language Constraints2010.05150v2 · Tsung-Yen Yang, Michael Hu, Yinlam Chow et al.2020 · 9 citationsarXiv
Control-Aware Representations for Model-based Reinforcement Learning2006.13408v1 · Brandon Cui, Yinlam Chow, Mohammad Ghavamzadeh2020 · 8 citationsarXiv
Non-Stationary Off-Policy Optimization2006.08236v3 · Joey Hong, Branislav Kveton, Manzil Zaheer et al.2020 · 2 citationsarXiv
Latent Bandits Revisited2006.08714v1 · Joey Hong, Branislav Kveton, Manzil Zaheer et al.2020 · 21 citationsarXiv
Variational Model-based Policy Optimization2006.05443v2 · Yinlam Chow, Brandon Cui, MoonKyung Ryu et al.2020 · 5 citationsarXiv
Predictive Coding for Locally-Linear Control2003.01086v1 · Rui Shu, Tung Nguyen, Yinlam Chow et al.2020 · 7 citationsarXiv
BRPO: Batch Residual Policy Optimization2002.05522v2 · Sungryull Sohn, Yinlam Chow, Jayden Ooi et al.2020 · 5 citationsarXiv
AlgaeDICE: Policy Gradient from Arbitrary Experience1912.02074v1 · Ofir Nachum, Bo Dai, Ilya Kostrikov et al.2019 · 74 citationsarXiv
CAQL: Continuous Action Q-Learning1909.12397v3 · Moonkyung Ryu, Yinlam Chow, Ross Anderson et al.2019 · 20 citationsarXiv
Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control1909.01506v2 · Nir Levine, Yinlam Chow, Rui Shu et al.2019 · 13 citationsarXiv
DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections1906.04733v2 · Ofir Nachum, Yinlam Chow, Bo Dai et al.2019 · 117 citationsarXiv
Lyapunov-based Safe Policy Optimization for Continuous Control1901.10031v2 · Yinlam Chow, Ofir Nachum, Aleksandra Faust et al.2019 · 151 citationsarXiv
A Block Coordinate Ascent Algorithm for Mean-Variance Optimization1809.02292v3 · Bo Liu, Tengyang Xie, Yangyang Xu et al.2018 · 23 citationsarXiv
Risk-Sensitive Generative Adversarial Imitation Learning1808.04468v2 · Jonathan Lacotte, Mohammad Ghavamzadeh, Yinlam Chow et al.2018 · 13 citationsarXiv
A Lyapunov-based Approach to Safe Reinforcement Learning1805.07708v1 · Yinlam Chow, Ofir Nachum, Edgar Duenez-Guzman et al.2018 · 248 citationsarXiv
More Robust Doubly Robust Off-policy Evaluation1802.03493v2 · Mehrdad Farajtabar, Yinlam Chow, Mohammad Ghavamzadeh2018 · 29 citationsarXiv
Path Consistency Learning in Tsallis Entropy Regularized MDPs1802.03501v1 · Ofir Nachum, Yinlam Chow, Mohammad Ghavamzadeh2018 · 23 citationsarXiv
A Framework for Time-Consistent, Risk-Sensitive Model Predictive Control: Theory and Algorithms1703.01029v2 · Sumeet Singh, Yin-Lam Chow, Anirudha Majumdar et al.2017 · 76 citationsarXiv
Safe Policy Improvement by Minimizing Robust Baseline Regret1607.03842v1 · Marek Petrik, Yinlam Chow, Mohammad Ghavamzadeh2016 · 85 citationsarXiv
Risk Aversion in Finite Markov Decision Processes Using Total Cost Criteria and Average Value at Risk1602.05130v1 · Stefano Carpin, Yin-Lam Chow, Marco Pavone2016 · 29 citationsarXiv
Weighted SGD for ℓ p Regression with Randomized Preconditioning.29782626 · Yang, Jiyan, Chow, Yin-Lam, Ré, Christopher et al.2024 · 16 citationsProceedings of the ... Annual ACM-SIAM Symposium on Discrete Algorithms. ACM-SIAM Symposium on Discrete Algorithms. 2016;2016:558-569
Risk-Constrained Reinforcement Learning with Percentile Risk Criteria1512.01629v3 · Yinlam Chow, Mohammad Ghavamzadeh, Lucas Janson et al.2015 · 212 citationsarXiv
Stochastic Optimal Control With Dynamic, Time-Consistent Risk Constraints1511.06980v1 · Yin-Lam Chow, Marco Pavone2015 · 15 citationsarXiv
A Framework for Time-Consistent, Risk-Averse Model Predictive Control: Theory and Algorithms1511.06981v1 · Yin-Lam Chow, Marco Pavone2015 · 30 citationsarXiv
Trading Safety Versus Performance: Rapid Deployment of Robotic Swarms with Robust Performance Constraints1511.06982v1 · Yin-Lam Chow, Marco Pavone, Brian M. Sadler et al.2015 · 19 citationsarXiv
Two Phase learning for Bidding-based Vehicle Sharing1509.08932v3 · Yinlam Chow, Jia Yuan Yu, Marco Pavone2015 · 3 citationsarXiv
Robust Policy Optimization with Baseline Guarantees1506.04514v2 · Yinlam Chow, Marek Petrik, Mohammad Ghavamzadeh2015 · 4 citationsarXiv
Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach1506.02188v1 · Yinlam Chow, Aviv Tamar, Shie Mannor et al.2015 · 143 citationsarXivon Valency
Policy Gradient for Coherent Risk Measures1502.03919v2 · Aviv Tamar, Yinlam Chow, Mohammad Ghavamzadeh et al.2015 · 63 citationsarXivon Valency
Weighted SGD for Regression with Randomized Preconditioning1502.03571v5 · Jiyan Yang, Yin-Lam Chow, Christopher R'e et al.2015 · 4 citationsarXiv
A Uniform-grid Discretization Algorithm for Stochastic Control with Risk Constraints1501.02024v1 · Yin-Lam Chow, Marco Pavone2015 · 0 citationsarXiv
Career total: 73 works. 55 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.