SM
Shie Mannor
cs.LGstat.MLcs.AIcs.SYeess.SYmath.OCcs.CVcs.ROcs.ITmath.IT
On Valency
published · living versionsW_d8cbc6rs·v1 · currentpublished
Policy Gradient for Coherent Risk Measures
with Aviv Tamar, Yinlam Chow, Mohammad Ghavamzadeh
1 version
W_ybywrwg8·v1published
Preprints & journals
252 papers in the corpus · 2007–2026Learning Graded Sparse Mechanisms: A Representation Theorem and Certified Generalization2610.16537v1 · Mark Kozdoba, Shie Mannor2026 · 0 citationsarXiv
Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair2610.15894v1 · Elad Sharony, Ido Greenberg, Jialin Song et al.2026 · 0 citationsarXiv
Reinforcement Learning with Segment Reward Feedback under Linear Function Approximation2610.08271v1 · Fengxu Liu, Siwei Wang, Gal Dalal et al.2026 · 0 citationsarXiv
COMPASS: Ordered Clustered Routing at 100K Scale2609.20352v1 · Ido Greenberg, Hugo Linsenmaier, Piotr Sielski et al.2026 · 0 citationsarXiv
Score the Algebra, Not the Span: Dimension Reduction for Transfer Operator Models of Dynamical Systems2608.18918v1 · Mark Kozdoba, Shie Mannor2026 · 0 citationsarXiv
Zero-Shot Active Feature Acquisition via LLM-Elicitation2606.18933v2 · Binyamin Perets, Natalie Mendelson, Shiran Vainberg et al.2026 · 0 citationsarXiv
Finite Resources False Discovery Rate Control in Structured Hypothesis Spaces2606.15393v1 · Binyamin Perets, Shie Mannor2026 · 0 citationsarXiv
Toward Micro-Endoscopy: Distal-Free, Configuration-Agnostic Focusing Through Multimode Fiber2605.28506v1 · Dvir Marsh, Lior Fridman, Stav Lotan et al.2026 · 0 citationsarXiv
Controlling False Discovery in Arbitrarily Structured Hypothesis Spaces via Reproducing Kernels2605.17559v1 · Binyamin Perets, Shie Mannor2026 · 0 citationsarXiv
The Value of Mechanistic Priors in Sequential Decision Making2605.10018v3 · Itai Shufaro, Gal Benor, Shie Mannor2026 · 0 citationsarXiv
Simulating clinical interventions with a generative multimodal model of human physiology2604.27899v1 · Guy Lutsker, Gal Sapir, Jordi Merino et al.2026 · 0 citationsarXiv
Cancer resistance to therapy by tissue-level homeostatic feedback10.64898/2026.03.25.714177v1 · Somer, J., Straussman, R., Alon, U. et al.2026 · 0 citationsbioRxiv
Time of Day as an Unmeasured Confounder in Oncology Trials10.64898/2026.03.05.26347742v1 · Somer, J., Benor, G., Alpert, A. et al.2026 · 0 citationsmedRxiv
Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models2602.08032v3 · Lior Cohen, Ofir Nabati, Kaixin Wang et al.2026 · 0 citationsarXiv
Optimal Sample Complexity for Single Time-Scale Actor-Critic with Momentum2602.01505v2 · Navdeep Kumar, Tehila Dahan, Lior Cohen et al.2026 · 0 citationsarXiv
VLM-Guided Experience Replay2602.01915v2 · Elad Sharony, Tom Jurgenson, Orr Krupnik et al.2026 · 0 citationsarXiv
Temporal tissue dynamics from a spatial snapshot.41565801 · Somer, Jonathan, Mannor, Shie, Alon, Uri2026 · 14 citationsNature. 2026;650(8101):490-499
A foundation model for continuous glucose monitoring data.41535468 · Lutsker, Guy, Sapir, Gal, Shilo, Smadar et al.2026 · 28 citationsNature. 2026;650(8103):978-986
Representative Action Selection for Large Action Space: From Bandits to MDPs2511.22104v1 · Quan Zhou, Shie Mannor2025 · 0 citationsarXiv
Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces2509.22963v3 · Haitong Ma, Ofir Nabati, Aviv Rosenberg et al.2025 · 0 citationsarXiv
OSDR2.0 infers microenvironment-driven cell-state transitions and population dynamics from a single spatial biopsy10.1101/2025.09.02.673328v1 · Ben Shalom, I., Somer, J., Miyara, S. et al.2025 · 0 citationsbioRxiv
Spectral Bellman Method: Unifying Representation and Exploration in RL2507.13181v2 · Ofir Nabati, Bo Dai, Shie Mannor et al.2025 · 0 citationsarXiv
Policy Gradient with Tree Search: Avoiding Local Optimas through Lookahead2506.07054v1 · Uri Koren, Navdeep Kumar, Uri Gadot et al.2025 · 0 citationsarXiv
State Entropy Regularization for Robust Reinforcement Learning2506.07085v3 · Yonatan Ashlag, Uri Koren, Mirco Mutti et al.2025 · 0 citationsarXiv
Policy Optimized Text-to-Image Pipeline Design2505.21478v2 · Uri Gadot, Rinon Gal, Yftah Ziser et al.2025 · 0 citationsarXiv
Hierarchical Adversarial Bandits for Online Configuration Optimization2505.19061v2 · Gil Shabat, Chen Avin, Shie Mannor et al.2025 · 0 citationsarXiv
Representative Action Selection for Large Action Space Bandit Families2505.18269v5 · Quan Zhou, Mark Kozdoba, Shie Mannor2025 · 0 citationsarXiv
Accelerating Vehicle Routing via AI-Initialized Genetic Algorithms2504.06126v2 · Ido Greenberg, Piotr Sielski, Hugo Linsenmaier et al.2025 · 0 citationsarXiv
A Classification View on Meta Learning Bandits2504.04505v1 · Mirco Mutti, Jeongyeol Kwon, Shie Mannor et al.2025 · 0 citationsarXiv
Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models2503.22886v2 · Ron Vainshtein, Zohar Rimon, Shie Mannor et al.2025 · 0 citationsarXiv
Simulus: Combining Improvements in Sample-Efficient World Model Agents2502.11537v4 · Lior Cohen, Kaixin Wang, Bingyi Kang et al.2025 · 0 citationsarXiv
Dual Formulation for Non-Rectangular Lp Robust Markov Decision Processes2502.09432v1 · Navdeep Kumar, Adarsh Gupta, Maxence Mohamed Elfatihi et al.2025 · 0 citationsarXiv
Reinforcement Learning with Segment Feedback2502.01876v2 · Yihan Du, Anna Winnicki, Gal Dalal et al.2025 · 0 citationsarXiv
RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression2501.12216v2 · Uri Gadot, Assaf Shocher, Shie Mannor et al.2025 · 4 citationsarXiv
Learning Multiple Initial Solutions to Optimization Problems2411.02158v2 · Elad Sharony, Heng Yang, Tong Che et al.2024 · 0 citationsarXiv
Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization2410.19471v1 · Ryan Park, Darren J. Hsu, C. Brian Roland et al.2024 · 2 citationsarXiv
On the Convergence of Single-Timescale Actor-Critic2410.08868v2 · Navdeep Kumar, Priyank Agrawal, Giorgia Ramponi et al.2024 · 0 citationsarXiv
Dual Pricing to Prioritize Renewable Energy and Consumer Preferences in Electricity Markets2409.18766v1 · Emilie Jong, Samuel Chevalier, Spyros Chatzivasileiadis et al.2024 · 0 citationsarXiv
Efficient Fairness-Performance Pareto Front Computation2409.17643v3 · Mark Kozdoba, Binyamin Perets, Shie Mannor2024 · 1 citationarXiv
From Glucose Patterns to Health Outcomes: A Generalizable Foundation Model for Continuous Glucose Monitor Data Analysis2408.11876v2 · Guy Lutsker, Gal Sapir, Smadar Shilo et al.2024 · 11 citationsarXiv
PlaMo: Plan and Move in Rich 3D Physical Environments2406.18237v1 · Assaf Hallak, Gal Dalal, Chen Tessler et al.2024 · 1 citationarXiv
RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation2406.01389v2 · Jeongyeol Kwon, Shie Mannor, Constantine Caramanis et al.2024 · 1 citationarXiv
On Bits and Bandits: Quantifying the Regret-Information Trade-off2405.16581v4 · Itai Shufaro, Nadav Merlis, Nir Weinberger et al.2024 · 0 citationsarXiv
Tree Search-Based Policy Optimization under Stochastic Execution Delay2404.05440v1 · David Valensi, Esther Derman, Shie Mannor et al.2024 · 1 citationarXiv
On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes2403.06806v1 · Navdeep Kumar, Yashaswini Murthy, Itai Shufaro et al.2024 · 0 citationsarXiv
Conservative DDPG -- Pessimistic RL without Ensemble2403.05732v2 · Nitsan Soffair, Shie Mannor2024 · 0 citationsarXiv
Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization2402.10342v2 · Yihan Du, Anna Winnicki, Gal Dalal et al.2024 · 1 citationarXiv
Improving Token-Based World Models with Parallel Observation Prediction2402.05643v5 · Lior Cohen, Kaixin Wang, Bingyi Kang et al.2024 · 0 citationsarXiv
SQT -- std -target2402.05950v3 · Nitsan Soffair, Dotan Di-Castro, Orly Avner et al.2024 · 0 citationsarXiv
MinMaxMin -learning2402.05951v3 · Nitsan Soffair, Shie Mannor2024 · 0 citationsarXiv
Career total: 676 works. 252 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.