research
∙
07/25/2023
The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation
Theoretical guarantees in reinforcement learning (RL) are known to suffe...
share
research
∙
06/22/2023
Context-lumpable stochastic bandits
We consider a contextual bandit problem with S contexts and A actions. I...
research
∙
05/22/2023
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
Mirror descent value iteration (MDVI), an abstraction of Kullback-Leible...
research
∙
05/18/2023
Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL
While policy optimization algorithms have played an important role in re...
research
∙
02/25/2023
Exponential Hardness of Reinforcement Learning with Linear Function Approximation
A fundamental question in reinforcement learning theory is: suppose the ...
research
∙
02/08/2023
Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning
A practical challenge in reinforcement learning are combinatorial action...
research
∙
01/29/2023
Sample Efficient Deep Reinforcement Learning via Local Planning
The focus of this work is sample-efficient deep reinforcement learning (...
research
∙
01/16/2023
The Role of Baselines in Policy Gradient Optimization
We study the effect of baselines in on-policy stochastic policy gradient...
research
∙
12/28/2022
Learning Lipschitz Functions by GD-trained Shallow Overparameterized ReLU Neural Networks
We explore the ability of overparameterized shallow ReLU neural networks...
research
∙
10/30/2022
Revisiting Simple Regret Minimization in Multi-Armed Bandits
Simple regret is a natural and parameter-free performance criterion for ...
research
∙
10/27/2022
Confident Approximate Policy Iteration for Efficient Local Planning in q^π-realizable MDPs
We consider approximate dynamic programming in γ-discounted Markov decis...
research
∙
09/29/2022
Optimistic MLE – A Generic Model-based Algorithm for Partially Observable Sequential Decision Making
This paper introduces a simple efficient learning algorithms for general...
research
∙
06/13/2022
Near-Optimal Sample Complexity Bounds for Constrained MDPs
In contrast to the advances in characterizing the sample complexity for ...
research
∙
06/05/2022
Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization
Directed Evolution (DE), a landmark wet-lab method originated in 1960s, ...
research
∙
06/02/2022
Sample-Efficient Reinforcement Learning of Partially Observable Markov Games
This paper considers the challenging tasks of Multi-Agent Reinforcement ...
research
∙
05/27/2022
KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal
In this work, we consider and analyze the sample complexity of model-fre...
research
∙
04/19/2022
When Is Partially Observable Reinforcement Learning Not Scary?
Applications of Reinforcement Learning (RL), in which agents learn to ma...
research
∙
04/11/2022
Towards Painless Policy Optimization for Constrained MDPs
We study policy optimization in an infinite horizon, γ-discounted constr...
research
∙
11/22/2021
A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning
Representation learning lies at the heart of the empirical success of de...
research
∙
10/29/2021
Understanding the Effect of Stochasticity in Policy Optimization
We study the effect of stochasticity in on-policy policy optimization, a...
research
∙
10/05/2021
TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions
We consider the minimax query complexity of online planning with a gener...
research
∙
08/12/2021
Efficient Local Planning with Linear Function Approximation
We study query and computationally efficient planning algorithms with li...
research
∙
07/27/2021
On the Role of Optimization in Double Descent: A Least Squares Study
Empirically it has been observed that the performance of deep neural net...
research
∙
07/13/2021
No Regrets for Learning the Prior in Bandits
We propose AdaTS, a Thompson sampling algorithm that adapts sequentially...
research
∙
07/12/2021
Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping
We explore the ability of overparameterized shallow neural networks to l...
research
∙
06/18/2021
On the Sample Complexity of Batch Reinforcement Learning with Policy-Induced Data
We study the fundamental question of the sample complexity of learning a...
research
∙
06/15/2021
On Multi-objective Policy Optimization as a Tool for Reinforcement Learning
Many advances that have improved the robustness and efficiency of deep r...
research
∙
05/13/2021
Leveraging Non-uniformity in First-order Non-convex Optimization
Classical global convergence results for first-order methods rely on uni...
research
∙
04/06/2021
On the Optimality of Batch Policy Optimization Algorithms
Batch policy optimization considers leveraging existing data for policy ...
research
∙
02/25/2021
Improved Regret Bound and Experience Replay in Regularized Policy Iteration
In this work, we study algorithms for learning in infinite-horizon undis...
research
∙
02/17/2021
On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method
Policy gradient gives rise to a rich class of reinforcement learning (RL...
research
∙
02/11/2021
Optimization Issues in KL-Constrained Approximate Policy Iteration
Many reinforcement learning algorithms can be seen as versions of approx...
research
∙
02/11/2021
Meta-Thompson Sampling
Efficient exploration in multi-armed bandits is a fundamental online lea...
research
∙
02/06/2021
Bootstrapping Statistical Inference for Off-Policy Evaluation
Bootstrapping provides a flexible and effective approach for assessing t...
research
∙
02/03/2021
On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function
We consider the problem of local planning in fixed-horizon Markov Decisi...
research
∙
12/15/2020
Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes
We study reinforcement learning (RL) with linear function approximation ...
research
∙
11/11/2020
Asymptotically Optimal Information-Directed Sampling
We introduce a computationally efficient algorithm for finite stochastic...
research
∙
11/08/2020
Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient
This paper provides a statistical analysis of high-dimensional batch Rei...
research
∙
11/08/2020
Online Sparse Reinforcement Learning
We investigate the hardness of online reinforcement learning in fixed ho...
research
∙
10/31/2020
On Optimality of Meta-Learning in Fixed-Design Regression with Weighted Biased Regularization
We consider a fixed-design linear regression in the meta-learning model ...
research
∙
10/23/2020
Online Algorithm for Unsupervised Sequential Selection with Contextual Information
In this paper, we study Contextual Unsupervised Sequential Selection (US...
research
∙
10/22/2020
CoinDICE: Off-Policy Confidence Interval Estimation
We study high-confidence behavior-agnostic off-policy evaluation in rein...
research
∙
10/03/2020
Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions
We consider the problem of local planning in fixed-horizon Markov Decisi...
research
∙
07/25/2020
Tighter risk certificates for neural networks
This paper presents empirical studies regarding training probabilistic n...
research
∙
07/13/2020
Efficient Planning in Large MDPs with Weak Linear Function Approximation
Large-scale Markov decision processes (MDPs) require planning algorithms...
research
∙
07/04/2020
Variational Policy Gradient Method for Reinforcement Learning with General Utilities
In recent years, reinforcement learning (RL) systems with general goals ...
research
∙
06/23/2020
PAC-Bayes Analysis Beyond the Usual Bounds
We focus on a stochastic learning model where the learner observes a fin...
research
∙
06/18/2020
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting
We consider off-policy evaluation in the contextual bandit setting for t...
research
∙
06/09/2020
Differentiable Meta-Learning in Contextual Bandits
We study a contextual bandit setting where the learning agent has access...
research
∙
06/01/2020