Author name cluster

Yaqi Duan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

11 papers

2 author rows

ICML Conference 2025 Conference Paper

PILAF: Optimal Human Preference Sampling for Reward Modeling

Yunzhen Feng
Ariel Kwiatkowski
Kunhao Zheng
Julia Kempe
Yaqi Duan

As large language models increasingly drive real-world applications, aligning them with human values becomes paramount. Reinforcement Learning from Human Feedback (RLHF) has emerged as a key technique, translating preference data into reward models when oracle human values remain inaccessible. In practice, RLHF mostly relies on approximate reward models, which may not consistently guide the policy toward maximizing the underlying human values. We propose Policy-Interpolated Learning for Aligned Feedback (PILAF), a novel response sampling strategy for preference labeling that explicitly aligns preference learning with maximizing the underlying oracle reward. PILAF is theoretically grounded, demonstrating optimality from both an optimization and a statistical perspective. The method is straightforward to implement and demonstrates strong performance in iterative and online RLHF settings where feedback curation is critical.

Details

NeurIPS Conference 2024 Conference Paper

Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces

Yaqi Duan
Martin J. Wainwright

We introduce a novel framework for analyzing reinforcement learning (RL) in continuous state-action spaces, and use it to prove fast rates of convergence in both off-line and on-line settings. Our analysis highlights two key stability properties, relating to how changes in value functions and/or policies affect the Bellman operator and occupation measures. We argue that these properties are satisfied in many continuous state-action Markov decision processes. Our analysis also offers fresh perspectives on the roles of pessimism and optimism in off-line and on-line RL.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Invertible Residual Neural Networks with Conditional Injector and Interpolator for Point Cloud Upsampling

Aihua Mao
Yaqi Duan
Yu-Hui Wen
Zihui Du
Hongmin Cai
Yong-Jin Liu

Point clouds obtained by LiDAR and other sensors are usually sparse and irregular. Low-quality point clouds have serious influence on the final performance of downstream tasks. Recently, a point cloud upsampling network with normalizing flows has been proposed to address this problem. However, the network heavily relies on designing specialized architectures to achieve invertibility. In this paper, we propose a novel invertible residual neural network for point cloud upsampling, called PU-INN, which allows unconstrained architectures to learn more expressive feature transformations. Then, we propose a conditional injector to improve nonlinear transformation ability of the neural network while guaranteeing invertibility. Furthermore, a lightweight interpolator is proposed based on semantic similarity distance in the latent space, which can intuitively reflect the interpolation changes in Euclidean space. Qualitative and quantitative results show that our method outperforms the state-of-the-art works in terms of distribution uniformity, proximity-to-surface accuracy, 3D reconstruction quality, and computation efficiency.

PDF Details DOI

JMLR Journal 2023 Journal Article

Learning Good State and Action Representations for Markov Decision Process via Tensor Decomposition

Chengzhuo Ni
Yaqi Duan
Munther Dahleh
Mengdi Wang
Anru R. Zhang

The transition kernel of a continuous-state-action Markov decision process (MDP) admits a natural tensor structure. This paper proposes a tensor-inspired unsupervised learning method to identify meaningful low-dimensional state and action representations from empirical trajectories. The method exploits the MDP's tensor structure by kernelization, importance sampling and low-Tucker-rank approximation. This method can be further used to cluster states and actions respectively and find the best discrete MDP abstraction. We provide sharp statistical error bounds for tensor concentration and the preservation of diffusion distance after embedding. We further prove that the learned state/action abstractions provide accurate approximations to latent block structures if they exist, enabling function approximation in downstream tasks such as policy evaluation. [abs] [ pdf ][ bib ] &copy JMLR 2023. ( edit, beta )

PDF Details

ICLR Conference 2022 Conference Paper

Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism

Ming Yin 0003
Yaqi Duan
Mengdi Wang 0001
Yu-Xiang Wang 0003

Offline reinforcement learning, which seeks to utilize offline/historical data to optimize sequential decision-making strategies, has gained surging prominence in recent studies. Due to the advantage that appropriate function approximators can help mitigate the sample complexity burden in modern reinforcement learning problems, existing endeavors usually enforce powerful function representation models (e.g. neural networks) to learn the optimal policies. However, a precise understanding of the statistical limits with function representations, remains elusive, even when such a representation is linear. Towards this goal, we study the statistical limits of offline reinforcement learning with linear model representations. To derive the tight offline learning bound, we design the variance-aware pessimistic value iteration (VAPVI), which adopts the conditional variance information of the value function for time-inhomogeneous episodic linear Markov decision processes (MDPs). VAPVI leverages estimated variances of the value functions to reweight the Bellman residuals in the least-square pessimistic value iteration and provides improved offline learning bounds over the best-known existing results (whereas the Bellman residuals are equally weighted by design). More importantly, our learning bounds are expressed in terms of system quantities, which provide natural instance-dependent characterizations that previous results are short of. We hope our results draw a clearer picture of what offline learning should look like when linear representations are provided.

Details

ICML Conference 2021 Conference Paper

Bootstrapping Fitted Q-Evaluation for Off-Policy Inference

Botao Hao
Xiang Ji
Yaqi Duan
Hao Lu
Csaba Szepesvári
Mengdi Wang 0001

Bootstrapping provides a flexible and effective approach for assessing the quality of batch reinforcement learning, yet its theoretical properties are poorly understood. In this paper, we study the use of bootstrapping in off-policy evaluation (OPE), and in particular, we focus on the fitted Q-evaluation (FQE) that is known to be minimax-optimal in the tabular and linear-model cases. We propose a bootstrapping FQE method for inferring the distribution of the policy evaluation error and show that this method is asymptotically efficient and distributionally consistent for off-policy statistical inference. To overcome the computation limit of bootstrapping, we further adapt a subsampling procedure that improves the runtime by an order of magnitude. We numerically evaluate the bootrapping method in classical RL environments for confidence interval estimation, estimating the variance of off-policy evaluator, and estimating the correlation between multiple off-policy evaluators.

Details

ICML Conference 2021 Conference Paper

Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning

Yaqi Duan
Chi Jin
ZhiYuan Li

This paper considers batch Reinforcement Learning (RL) with general value function approximation. Our study investigates the minimal assumptions to reliably estimate/minimize Bellman error, and characterizes the generalization performance by (local) Rademacher complexities of general function classes, which makes initial steps in bridging the gap between statistical learning theory and batch RL. Concretely, we view the Bellman error as a surrogate loss for the optimality gap, and prove the followings: (1) In double sampling regime, the excess risk of Empirical Risk Minimizer (ERM) is bounded by the Rademacher complexity of the function class. (2) In the single sampling regime, sample-efficient risk minimization is not possible without further assumptions, regardless of algorithms. However, with completeness assumptions, the excess risk of FQI and a minimax style algorithm can be again bounded by the Rademacher complexity of the corresponding function classes. (3) Fast statistical rates can be achieved by using tools of local Rademacher complexity. Our analysis covers a wide range of function classes, including finite classes, linear spaces, kernel spaces, sparse linear features, etc.

Details

ICML Conference 2021 Conference Paper

Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient

Botao Hao
Yaqi Duan
Tor Lattimore
Csaba Szepesvári
Mengdi Wang 0001

This paper provides a statistical analysis of high-dimensional batch reinforcement learning (RL) using sparse linear function approximation. When there is a large number of candidate features, our result sheds light on the fact that sparsity-aware methods can make batch RL more sample efficient. We first consider the off-policy policy evaluation problem. To evaluate a new target policy, we analyze a Lasso fitted Q-evaluation method and establish a finite-sample error bound that has no polynomial dependence on the ambient dimension. To reduce the Lasso bias, we further propose a post model-selection estimator that applies fitted Q-evaluation to the features selected via group Lasso. Under an additional signal strength assumption, we derive a sharper instance-dependent error bound that depends on a divergence function measuring the distribution mismatch between the data distribution and occupancy measure of the target policy. Further, we study the Lasso fitted Q-iteration for batch policy optimization and establish a finite-sample error bound depending on the ratio between the number of relevant features and restricted minimal eigenvalue of the data’s covariance. In the end, we complement the results with minimax lower bounds for batch-data policy evaluation/optimization that nearly match our upper bounds. The results suggest that having well-conditioned data is crucial for sparse batch policy learning.

Details

ICML Conference 2020 Conference Paper

Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation

Yaqi Duan
Zeyu Jia
Mengdi Wang 0001

This paper studies the statistical theory of off-policy evaluation with function approximation in batch data reinforcement learning problem. We consider a regression-based fitted Q-iteration method, show that it is equivalent to a model-based method that estimates a conditional mean embedding of the transition operator, and prove that this method is information-theoretically optimal and has nearly minimal estimation error. In particular, by leveraging contraction property of Markov processes and martingale concentration, we establish a finite-sample instance-dependent error upper bound and a nearly-matching minimax lower bound. The policy evaluation error depends sharply on a restricted $\chi^2$-divergence over the function class between the long-term distribution of target policy and the distribution of past data. This restricted $\chi^2$-divergence characterizes the statistical limit of off-policy evaluation and is both instance-dependent and function-class-dependent. Further, we provide an easily computable confidence bound for the policy evaluator, which may be useful for optimistic planning and safe policy improvement.

Details

NeurIPS Conference 2019 Conference Paper

Learning low-dimensional state embeddings and metastable clusters from time series data

Yifan Sun
Yaqi Duan
Hao Gong
Mengdi Wang

This paper studies how to find compact state embeddings from high-dimensional Markov state trajectories, where the transition kernel has a small intrinsic rank. In the spirit of diffusion map, we propose an efficient method for learning a low-dimensional state embedding and capturing the process's dynamics. This idea also leads to a kernel reshaping method for more accurate nonparametric estimation of the transition function. State embedding can be used to cluster states into metastable sets, thereby identifying the slow dynamics. Sharp statistical error bounds and misclassification rate are proved. Experiment on a simulated dynamical system shows that the state clustering method indeed reveals metastable structures. We also experiment with time series generated by layers of a Deep-Q-Network when playing an Atari game. The embedding method identifies game states to be similar if they share similar future events, even though their raw data are far different.

PDF Details

NeurIPS Conference 2019 Conference Paper

State Aggregation Learning from Markov Transition Data

Yaqi Duan
Tracy Ke
Mengdi Wang

State aggregation is a popular model reduction method rooted in optimal control. It reduces the complexity of engineering systems by mapping the system’s states into a small number of meta-states. The choice of aggregation map often depends on the data analysts’ knowledge and is largely ad hoc. In this paper, we propose a tractable algorithm that estimates the probabilistic aggregation map from the system’s trajectory. We adopt a soft-aggregation model, where each meta-state has a signature raw state, called an anchor state. This model includes several common state aggregation models as special cases. Our proposed method is a simple two- step algorithm: The first step is spectral decomposition of empirical transition matrix, and the second step conducts a linear transformation of singular vectors to find their approximate convex hull. It outputs the aggregation distributions and disaggregation distributions for each meta-state in explicit forms, which are not obtainable by classical spectral methods. On the theoretical side, we prove sharp error bounds for estimating the aggregation and disaggregation distributions and for identifying anchor states. The analysis relies on a new entry-wise deviation bound for singular vectors of the empirical transition matrix of a Markov process, which is of independent interest and cannot be deduced from existing literature. The application of our method to Manhattan traffic data successfully generates a data-driven state aggregation map with nice interpretations.

PDF Details