Author name cluster

Yi Wan

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.

9 papers

2 author rows

JBHI Journal 2026 Journal Article

Hybrid Dual-Heterogeneous Knowledge Distillation Network for Anomaly Detection in Retinal OCT Images

Muhao Xu
Hua Wei
Zihan Nie
Xueying Zhou
Baochen Fu
Hongmei Yan
Yi Wan
Weiye Song

Unsupervised medical anomaly detection aims to identify abnormal images by training exclusively on normal samples, thereby enabling the detection of disease related irregularities without the need for large-scale labeled datasets. Current knowledge distillation-based methods typically detect anomalies by comparing feature discrepancies between teacher and student networks. However, because these methods employ an optimization strategy where the teacher and student architectures are highly similar, the student network's features tend to closely mirror those of the teacher, leading to an identity mapping issue. Moreover, the diversity of lesion types in retinal Optical Coherence Tomography (OCT) images further complicates anomaly detection. In this paper, we propose a novel hybrid dual-heterogeneous knowledge distillation network to overcome these challenges. Our approach consists of a teacher network with an encoder-only architecture and a student network that integrates an encoder with dual decoders. This heterogeneous design effectively mitigates the identity mapping problem, enhancing sensitivity to both structural and logical anomalies. Specifically, our Multi Feature Model leverages convolutional and depthwise convolutional blocks to extract and integrate local features for structural anomaly detection, while the Mamba UpNet employs self-supervised learning to capture long-range dependencies and global anomaly patterns. Extensive experiments on two retinal OCT anomaly detection datasets demonstrate that our method achieves state-of-the-art performance, effectively handling diverse anomaly types. The source code is available at https://github.com/Xmh L/HDHKD.

Details DOI

AAAI Conference 2026 Conference Paper

SkySplat: Generalizable 3D Gaussian Splatting from Multi-Temporal Sparse Satellite Images

Xuejun Huang
Xinyi Liu
Yi Wan
Zhi Zheng
Bin Zhang
Mingtao Xiong
Yingying Pei
Yongjun Zhang

Three-dimensional scene reconstruction from sparse-view satellite images is a long-standing and challenging task. While 3D Gaussian Splatting (3DGS) and its variants have recently attracted attention for its high efficiency, existing methods remain unsuitable for satellite images due to incompatibility with rational polynomial coefficient (RPC) models and limited generalization capability. Recent advances in generalizable 3DGS approaches show potential, but they perform poorly on multi-temporal sparse satellite images due to limited geometric constraints, transient objects, and radiometric inconsistencies. To address these limitations, we propose SkySplat, a novel self-supervised framework that integrates the RPC model into the generalizable 3DGS pipeline, enabling more effective use of sparse geometric cues for improved reconstruction. SkySplat relies only on RGB images and radiometric-robust relative height supervision, thereby eliminating the need for ground-truth height maps. Key components include a Cross-Self Consistency Module (CSCM), which mitigates transient object interference via consistency-based masking, and a multi-view consistency aggregation strategy that refines reconstruction results. Compared to per-scene optimization methods, SkySplat achieves an 86 times speedup over EOGS with higher accuracy. It also outperforms generalizable 3DGS baselines, reducing MAE from 13.18 m to 1.80 m on the DFC19 dataset significantly, and demonstrates strong cross-dataset generalization on the MVS3D benchmark.

PDF Details DOI

JMLR Journal 2024 Journal Article

Pearl: A Production-Ready Reinforcement Learning Agent

Zheqing Zhu
Rodrigo de Salvo Braz
Jalaj Bhandari
Daniel Jiang
Yi Wan
Yonathan Efroni
Liyuan Wang
Ruiyang Xu

Reinforcement learning (RL) is a versatile framework for optimizing long-term goals. Although many real-world problems can be formalized with RL, learning and deploying a performant RL policy requires a system designed to address several important challenges, including the exploration-exploitation dilemma, partial observability, dynamic action spaces, and safety concerns. While the importance of these challenges has been well recognized, existing open-source RL libraries do not explicitly address them. This paper introduces Pearl, a Production-Ready RL software package designed to embrace these challenges in a modular way. In addition to presenting benchmarking results, we also highlight examples of Pearl's ongoing industry adoption to demonstrate its advantages for production use cases. Pearl is open sourced on GitHub at github.com/facebookresearch/pearl and its official website is pearlagent.github.io. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2024. ( edit, beta )

PDF Details

RLC Conference 2024 Conference Paper

Reward Centering

Abhishek Naik
Yi Wan
Manan Tomar
Richard S. Sutton

We show that discounted methods for solving continuing reinforcement learning problems can perform significantly better if they center their rewards by subtracting out the rewards' empirical average. The improvement is substantial at commonly used discount factors and increases further as the discount factor approaches one. In addition, we show that if a _problem's_ rewards are shifted by a constant, then standard methods perform much worse, whereas methods with reward centering are unaffected. Estimating the average reward is straightforward in the on-policy setting; we propose a slightly more sophisticated method for the off-policy setting. Reward centering is a general idea, so we expect almost every reinforcement-learning algorithm to benefit by the addition of reward centering.

PDF Details

RLJ Journal 2024 Journal Article

Reward Centering

Abhishek Naik
Yi Wan
Manan Tomar
Richard S. Sutton

PDF Details

UAI Conference 2023 Conference Paper

Loosely consistent emphatic temporal-difference learning

Jiamin He
Fengdi Che
Yi Wan
A. Rupam Mahmood

There has been significant interest in searching for off-policy Temporal-Difference (TD) algorithms that find the same solution that would have been obtained in the on-policy regime. An important property of such algorithms is that their expected update has the same fixed point as that of On-policy TD($\lambda$), which we call loose consistency. Notably, Full-IS-TD($\lambda$) is the only existing loosely consistent method under general linear function approximation but, unfortunately, has a high variance and is scarcely practical. This notorious high variance issue motivates the introduction of ETD($\lambda$), which tames down the variance but has a biased fixed point. Inspired by these two methods, we propose a new loosely consistent algorithm called Average Emphatic TD (AETD($\lambda$)) with a transient bias, which strikes a balance between bias and variance. Further, we unify AETD($\lambda$) with existing methods and obtain a new family of loosely consistent algorithms called Loosely Consistent Emphatic TD (LC-ETD($\lambda$, $\beta$, $\nu$)), which can control a smooth bias-variance trade-off by varying the speed at which the transient bias fades. Through experiments on illustrative examples, we show the effectiveness and practicality of LC-ETD($\lambda$, $\beta$, $\nu$).

Details

ICML Conference 2022 Conference Paper

Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods

Yi Wan
Ali Rahimi-Kalahroudi
Janarthanan Rajendran
Ida Momennejad
Sarath Chandar
Harm van Seijen

In recent years, a growing number of deep model-based reinforcement learning (RL) methods have been introduced. The interest in deep model-based RL is not surprising, given its many potential benefits, such as higher sample efficiency and the potential for fast adaption to changes in the environment. However, we demonstrate, using an improved version of the recently introduced Local Change Adaptation (LoCA) setup, that well-known model-based methods such as PlaNet and DreamerV2 perform poorly in their ability to adapt to local environmental changes. Combined with prior work that made a similar observation about the other popular model-based method, MuZero, a trend appears to emerge, suggesting that current deep model-based methods have serious limitations. We dive deeper into the causes of this poor performance, by identifying elements that hurt adaptive behavior and linking these to underlying techniques frequently used in deep model-based RL. We empirically validate these insights in the case of linear function approximation by demonstrating that a modified version of linear Dyna achieves effective adaptation to local changes. Furthermore, we provide detailed insights into the challenges of building an adaptive nonlinear model-based method, by experimenting with a nonlinear version of Dyna.

Details

NeurIPS Conference 2021 Conference Paper

Average-Reward Learning and Planning with Options

Yi Wan
Abhishek Naik
Rich Sutton

We extend the options framework for temporal abstraction in reinforcement learning from discounted Markov decision processes (MDPs) to average-reward MDPs. Our contributions include general convergent off-policy inter-option learning algorithms, intra-option algorithms for learning values and models, as well as sample-based planning variants of our learning algorithms. Our algorithms and convergence proofs extend those recently developed by Wan, Naik, and Sutton. We also extend the notion of option-interrupting behaviour from the discounted to the average-reward formulation. We show the efficacy of the proposed algorithms with experiments on a continuing version of the Four-Room domain.

PDF Details

IJCAI Conference 2019 Conference Paper

Planning with Expectation Models

Yi Wan
Muhammad Zaheer
Adam White
Martha White
Richard S. Sutton

Distribution and sample models are two popular model choices in model-based reinforcement learning (MBRL). However, learning these models can be intractable, particularly when the state and action spaces are large. Expectation models, on the other hand, are relatively easier to learn due to their compactness and have also been widely used for deterministic environments. For stochastic environments, it is not obvious how expectation models can be used for planning as they only partially characterize a distribution. In this paper, we propose a sound way of using approximate expectation models for MBRL. In particular, we 1) show that planning with an expectation model is equivalent to planning with a distribution model if the state value function is linear in state features, 2) analyze two common parametrization choices for approximating the expectation: linear and non-linear expectation models, 3) propose a sound model-based policy evaluation algorithm and present its convergence results, and 4) empirically demonstrate the effectiveness of the proposed planning algorithm.

PDF Details