Longbo Huang

papers

785

total citations

papers (16)

Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits

NEURIPS 2020arXiv

citations

The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition

NEURIPS 2021arXiv

citations

Multi-Agent Reinforcement Learning in Stochastic Networked Systems

NEURIPS 2021arXiv

citations

Provable Generalization of Overparameterized Meta-learning Trained with SGD

NEURIPS 2022arXiv

citations

Provably Safe Reinforcement Learning with Step-wise Violation Constraints

NEURIPS 2023arXiv

citations

uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs

ICLR 2025arXiv

citations

Continuous Mean-Covariance Bandits

NEURIPS 2021arXiv

citations

RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning

ICML 2024arXiv

citations

A Quadratic Synchronization Rule for Distributed Deep Learning

ICLR 2024arXiv

citations

Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation

ICML 2024arXiv

citations

Finite-Time Analysis of Discrete-Time Stochastic Interpolants

ICML 2025arXiv

citations

Regularized Softmax Deep Multi-Agent Q-Learning

NEURIPS 2021

citations

Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight Observation

ICML 2024arXiv

citations

Longbo Huang

papers (16)

What Makes Multi-Modal Learning Better than Single (Provably)

Fast Federated Learning in the Presence of Arbitrary Device Unavailability

Softmax Deep Double Deterministic Policy Gradients

Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits

The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition

Multi-Agent Reinforcement Learning in Stochastic Networked Systems

Provable Generalization of Overparameterized Meta-learning Trained with SGD

Provably Safe Reinforcement Learning with Step-wise Violation Constraints

uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs

Continuous Mean-Covariance Bandits

RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning

A Quadratic Synchronization Rule for Distributed Deep Learning

Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation

Finite-Time Analysis of Discrete-Time Stochastic Interpolants

Regularized Softmax Deep Multi-Agent Q-Learning

Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight Observation

papers (16)

What Makes Multi-Modal Learning Better than Single (Provably)

Fast Federated Learning in the Presence of Arbitrary Device Unavailability

Softmax Deep Double Deterministic Policy Gradients

Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits

The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition

Multi-Agent Reinforcement Learning in Stochastic Networked Systems

Provable Generalization of Overparameterized Meta-learning Trained with SGD

Provably Safe Reinforcement Learning with Step-wise Violation Constraints

uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs

Continuous Mean-Covariance Bandits

RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning

A Quadratic Synchronization Rule for Distributed Deep Learning

Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation

Finite-Time Analysis of Discrete-Time Stochastic Interpolants

Regularized Softmax Deep Multi-Agent Q-Learning

Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight Observation