research
∙
08/17/2023
Model-Free Algorithm with Improved Sample Efficiency for Zero-Sum Markov Games
The problem of two-player zero-sum Markov games has recently attracted i...
share
research
∙
08/10/2023
Provably Efficient Algorithm for Nonstationary Low-Rank MDPs
Reinforcement learning (RL) under changing environment models many real-...
research
∙
08/07/2023
Non-Convex Bilevel Optimization with Time-Varying Objective Functions
Bilevel optimization has become a powerful tool in a wide variety of mac...
research
∙
08/01/2023
Doubly Robust Instance-Reweighted Adversarial Training
Assigning importance weights to adversarial data has achieved great succ...
research
∙
07/01/2023
Provably Efficient UCB-type Algorithms For Learning Predictive State Representations
The general sequential decision-making problem, which includes Markov de...
research
∙
06/14/2023
Theoretical Hardness and Tractability of POMDPs in RL with Partial Hindsight State Information
Partially observable Markov decision processes (POMDPs) have been widely...
research
∙
06/08/2023
Generalization Performance of Transfer Learning: Overparameterized and Underparameterized Regimes
Transfer learning is a useful technique for achieving improved performan...
research
∙
06/01/2023
Non-stationary Reinforcement Learning under General Function Approximation
General function approximation is a powerful tool to handle large state ...
research
∙
04/09/2023
Theoretical Characterization of the Generalization Performance of Overfitted Meta-Learning
Meta-learning has arisen as a successful method for improving training p...
research
∙
03/20/2023
Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs
In reward-free reinforcement learning (RL), an agent explores the enviro...
research
∙
02/28/2023
M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation
Learning to Optimize (L2O) has drawn increasing attention as it often re...
research
∙
02/22/2023
Learning to Generalize Provably in Learning to Optimize
Learning to optimize (L2O) has gained increasing popularity, which autom...
research
∙
02/12/2023
Theory on Forgetting and Generalization of Continual Learning
Continual learning (CL), which aims to learn a sequence of tasks, has at...
research
∙
02/08/2023
A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints
In many applications of Reinforcement Learning (RL), it is critically im...
research
∙
02/08/2023
Near-Optimal Adversarial Reinforcement Learning with Switching Costs
Switching costs, which capture the costs for changing policies, are rega...
research
∙
02/02/2023
Algorithm Design for Online Meta-Learning with Task Boundary Detection
Online meta-learning has recently emerged as a marriage between batch me...
research
∙
01/01/2023
Theoretical Characterization of How Neural Network Pruning Affects its Generalization
It has been observed in practice that applying pruning-at-initialization...
research
∙
01/01/2023
Sharper analysis of sparsely activated wide neural networks with trainable biases
This work studies training one-hidden-layer overparameterized ReLU netwo...
research
∙
08/18/2022
Global Convergence of Two-timescale Actor-Critic for Solving Linear Quadratic Regulator
The actor-critic (AC) reinforcement learning algorithms have been the po...
research
∙
06/28/2022
Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL
While the primary goal of the exploration phase in reward-free reinforce...
research
∙
06/18/2022
Provable Generalization of Overparameterized Meta-learning Trained with SGD
Despite the superior empirical success of deep meta-learning, theoretica...
research
∙
06/13/2022
Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward
The remarkable success of reinforcement learning (RL) heavily relies on ...
research
∙
06/13/2022
Provable Benefit of Multitask Representation Learning in Reinforcement Learning
As representation learning becomes a powerful technique to reduce sample...
research
∙
05/27/2022
Will Bilevel Optimizers Benefit from Loops
Bilevel optimization has arisen as a powerful tool for solving a variety...
research
∙
03/31/2022
Data Sampling Affects the Complexity of Online SGD over Dependent Data
Conventional machine learning applications typically assume that data sa...
research
∙
03/01/2022
A Constrained Optimization Approach to Bilevel Optimization with Multiple Inner Minima
Bilevel optimization has found extensive applications in modern machine ...
research
∙
02/07/2022
Model-Based Offline Meta-Reinforcement Learning with Regularization
Existing offline reinforcement learning (RL) methods face a few major ch...
research
∙
10/20/2021
Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process
The problem of constrained Markov decision process (CMDP) is investigate...
research
∙
10/13/2021
ES-Based Jacobian Enables Faster Bilevel Optimization
Bilevel optimization (BO) has arisen as a powerful tool for solving many...
research
∙
10/13/2021
PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method
Emphatic temporal difference (ETD) learning (Sutton et al., 2016) is a s...
research
∙
07/06/2021
A Unified Off-Policy Evaluation Approach for General Value Function
General Value Function (GVF) is a powerful tool to represent both the pr...
research
∙
06/08/2021
Provably Faster Algorithms for Bilevel Optimization
Bilevel optimization has been widely applied in many important machine l...
research
∙
02/23/2021
Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality
Designing off-policy reinforcement learning algorithms is typically a ve...
research
∙
02/09/2021
Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry
The gradient descent-ascent (GDA) algorithm has been widely applied to s...
research
∙
02/07/2021
Lower Bounds and Accelerated Algorithms for Bilevel Optimization
Bilevel optimization has recently attracted growing interests due to its...
research
∙
11/11/2020
A Primal Approach to Constrained Policy Optimization: Global Optimality and Finite-Time Analysis
Safe reinforcement learning (SRL) problems are typically modeled as cons...
research
∙
11/10/2020
Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning Algorithms
Two timescale stochastic approximation (SA) has been widely used in valu...
research
∙
10/15/2020
Provably Faster Algorithms for Bilevel Optimization and Applications to Meta-Learning
Bilevel optimization has arisen as a powerful tool for many machine lear...
research
∙
09/29/2020
Finite-Time Analysis for Double Q-learning
Although Q-learning is one of the most successful algorithms for finding...
research
∙
08/09/2020
Spectral Algorithms for Community Detection in Directed Networks
Community detection in large social networks is affected by degree heter...
research
∙
07/30/2020
Momentum Q-learning with Finite-Sample Convergence Guarantee
Existing studies indicate that momentum ideas in conventional optimizati...
research
∙
07/29/2020
Feedback Capacities of Gaussian Multiple-Access Wiretap Channels
The feedback capacities of the Gaussian multiple-access channel (GMAC) a...
research
∙
07/15/2020
Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent
Existing convergence analyses of Q-learning mostly focus on the vanilla ...
research
∙
06/24/2020
When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence
Generative adversarial imitation learning (GAIL) is a popular inverse re...
research
∙
06/16/2020
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters
Although model-agnostic meta-learning (MAML) is a very successful algori...
research
∙
06/16/2020
Enhanced First and Zeroth Order Variance Reduced Algorithms for Min-Max Optimization
Min-max optimization captures many important machine learning problems s...
research
∙
05/07/2020
Non-asymptotic Convergence Analysis of Two Time-scale (Natural) Actor-Critic Algorithms
As an important type of reinforcement learning algorithms, actor-critic ...
research
∙
04/27/2020
Improving Sample Complexity Bounds for Actor-Critic Algorithms
The actor-critic (AC) algorithm is a popular method to find an optimal p...
research
∙
02/26/2020
Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization
Various types of parameter restart schemes have been proposed for accele...
research
∙
02/18/2020
