Gal Dalal

发表

Safe Exploration in Continuous Action Spaces pdf

Yuval Tassa, Krishnamurthy Dvijotham, Todd Hester, 2018, ArXiv.

Concentration Bounds for Two Timescale Stochastic Approximation with Applications to Reinforcement Learning pdf

Shie Mannor, Balázs Szörényi, Gugan Thoppe, 2017, ArXiv.

Reinforcement Learning with a Terminator

Assaf Hallak, Shie Mannor, Gal Dalal, 2022, ArXiv.

Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs

Shie Mannor, Gal Dalal, Chen Tessler, 2022, 2207.02295.

Reinforcement Learning for Datacenter Congestion Control

Doron Haritan Kazakov, Shie Mannor, Gal Dalal, 2021, AAAI.

Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs

Shie Mannor, Gal Dalal, Chen Tessler, 2022, ArXiv.

Planning and Learning with Adaptive Lookahead

Aviv A. Rosenberg, Assaf Hallak, Shie Mannor, 2022, AAAI.

Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction pdf

Shie Mannor, Gal Chechik, Iuri Frosio, 2021, NeurIPS.

Hierarchical Decision Making In Electricity Grid Management pdf

Shie Mannor, Elad Gilboa, Gal Dalal, 2016, ICML.

Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs

Shie Mannor, Gal Dalal, Gal Chechik, 2022, 2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing (CCGrid).

Finite Sample Analyses for TD(0) With Function Approximation

Shie Mannor, Balázs Szörényi, Gugan Thoppe, 2017, AAAI.

A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound pdf

Balázs Szörényi, Gugan Thoppe, Gal Dalal, 2019, AAAI.

Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning

Shie Mannor, Balázs Szörényi, Gugan Thoppe, 2017, COLT.

Multiple-Step Greedy Policies in Approximate and Online Reinforcement Learning

Shie Mannor, Bruno Scherrer, Yonathan Efroni, 2018, NeurIPS.

Distributed scenario-based optimization for asset management in a hierarchical decision making environment

Shie Mannor, Elad Gilboa, Gal Dalal, 2016, 2016 Power Systems Computation Conference (PSCC).

Unit Commitment Using Nearest Neighbor as a Short-Term Proxy

Shie Mannor, Louis Wehenkel, Elad Gilboa, 2016, 2018 Power Systems Computation Conference (PSCC).

Acting in Delayed Environments with Non-Stationary Markov Policies pdf

Shie Mannor, Gal Dalal, Esther Derman, 2021, ICLR.

Multiple-Step Greedy Policies in Online and Approximate Reinforcement Learning pdf

Shie Mannor, Bruno Scherrer, Yonathan Efroni, 2018, NIPS 2018.

Beyond the One Step Greedy Approach in Reinforcement Learning

Shie Mannor, Bruno Scherrer, Yonathan Efroni, 2018, ICML.

On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning pdf

Shie Mannor, Gal Chechik, Uri Shalit, 2021, ICLR.

How to Combine Tree-Search Methods in Reinforcement Learning

Shie Mannor, Bruno Scherrer, Yonathan Efroni, 2018, AAAI.

SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search

Assaf Hallak, Shie Mannor, Gal Dalal, 2023, ArXiv.

Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction

Assaf Hallak, Shie Mannor, Gal Dalal, 2021, NeurIPS.

On the Products of Stochastic and Diagonal Matrices

Assaf Hallak, Gal Dalal, 2023, arXiv.org.

SoftTreeMax: Policy Gradient with Tree Search

Assaf Hallak, Shie Mannor, Gal Dalal, 2022, ArXiv.

Acting in Delayed Environments with Non-Stationary Markov Policies

Shie Mannor, E. Derman, Gal Dalal, 2021, International Conference on Learning Representations.

Chance-Constrained Outage Scheduling Using a Machine Learning Proxy

Shie Mannor, Louis Wehenkel, Elad Gilboa, 2018, IEEE Transactions on Power Systems.

Finite Sample Analysis for TD(0) with Linear Function Approximation pdf

Shie Mannor, Balázs Szörényi, Gugan Thoppe, 2017, ArXiv.

AutoScratch: ML-Optimized Cache Management for Inference-Oriented GPUs

Gal Dalal, A. Jaleel, Shie Mannor, 2023, MLSys.

Supervised learning for optimal power flow as a real-time proxy

Shie Mannor, Gal Dalal, Raphaël Canyasse, 2016, 2017 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT).