Xu Tian

Fan-Ming Luo, Tian Xu, Hang Lai et al.

Reinforcement learning (RL) solves sequential decision-making problems via a trial-and-error process interacting with the environment. While RL achieves outstanding success in playing complex video games that allow huge trial-and-error, making errors is always undesired in the real world. To improve the sample efficiency and thus reduce the errors, model-based reinforcement learning (MBRL) is believed to be a promising direction, which builds environment models in which the trial-and-errors can take place without real costs. In this survey, we take a review of MBRL with a focus on the recent progress in deep RL. For non-tabular environments, there is always a generalization error between the learned environment model and the real environment. As such, it is of great importance to analyze the discrepancy between policy training in the environment model and that in the real environment, which in turn guides the algorithm design for better model learning, model usage, and policy training. Besides, we also discuss the recent advances of model-based techniques in other forms of RL, including offline RL, goal-conditioned RL, multi-agent RL, and meta-RL. Moreover, we discuss the applicability and advantages of MBRL in real-world tasks. Finally, we end this survey by discussing the promising prospects for the future development of MBRL. We think that MBRL has great potential and advantages in real-world applications that were overlooked, and we hope this survey could attract more research on MBRL.

Tian Xu, Ziniu Li, Yang Yu et al.

Imitation learning learns a policy from expert trajectories. While the expert data is believed to be crucial for imitation quality, it was found that a kind of imitation learning approach, adversarial imitation learning (AIL), can have exceptional performance. With as little as only one expert trajectory, AIL can match the expert performance even in a long horizon, on tasks such as locomotion control. There are two mysterious points in this phenomenon. First, why can AIL perform well with only a few expert trajectories? Second, why does AIL maintain good performance despite the length of the planning horizon? In this paper, we theoretically explore these two questions. For a total-variation-distance-based AIL (called TV-AIL), our analysis shows a horizon-free imitation gap $\mathcal O(\{\min\{1, \sqrt{|\mathcal S|/N} \})$ on a class of instances abstracted from locomotion control tasks. Here $|\mathcal S|$ is the state space size for a tabular Markov decision process, and $N$ is the number of expert trajectories. We emphasize two important features of our bound. First, this bound is meaningful in both small and large sample regimes. Second, this bound suggests that the imitation gap of TV-AIL is at most 1 regardless of the planning horizon. Therefore, this bound can explain the empirical observation. Technically, we leverage the structure of multi-stage policy optimization in TV-AIL and present a new stage-coupled analysis via dynamic programming

Xu Tian, Jin Liu, Hulin Kuang et al.

Accurately detecting Alzheimer's disease (AD) and predicting mini-mental state examination (MMSE) score are important tasks in elderly health by magnetic resonance imaging (MRI). Most of the previous methods on these two tasks are based on single-task learning and rarely consider the correlation between them. Since the MMSE score, which is an important basis for AD diagnosis, can also reflect the progress of cognitive impairment, some studies have begun to apply multi-task learning methods to these two tasks. However, how to exploit feature correlation remains a challenging problem for these methods. To comprehensively address this challenge, we propose a MRI-based multi-task decoupled learning method for AD detection and MMSE score prediction. First, a multi-task learning network is proposed to implement AD detection and MMSE score prediction, which exploits feature correlation by adding three multi-task interaction layers between the backbones of the two tasks. Each multi-task interaction layer contains two feature decoupling modules and one feature interaction module. Furthermore, to enhance the generalization between tasks of the features selected by the feature decoupling module, we propose the feature consistency loss constrained feature decoupling module. Finally, in order to exploit the specific distribution information of MMSE score in different groups, a distribution loss is proposed to further enhance the model performance. We evaluate our proposed method on multi-site datasets. Experimental results show that our proposed multi-task decoupled representation learning method achieves good performance, outperforming single-task learning and other existing state-of-the-art methods.

Tian Xu, Ziniu Li, Yang Yu et al.

Imitation learning (IL) has proven to be an effective method for learning good policies from expert demonstrations. Adversarial imitation learning (AIL), a subset of IL methods, is particularly promising, but its theoretical foundation in the presence of unknown transitions has yet to be fully developed. This paper explores the theoretical underpinnings of AIL in this context, where the stochastic and uncertain nature of environment transitions presents a challenge. We examine the expert sample complexity and interaction complexity required to recover good policies. To this end, we establish a framework connecting reward-free exploration and AIL, and propose an algorithm, MB-TAIL, that achieves the minimax optimal expert sample complexity of $\widetilde{O} (H^{3/2} |S|/\varepsilon)$ and interaction complexity of $\widetilde{O} (H^{3} |S|^2 |A|/\varepsilon^2)$. Here, $H$ represents the planning horizon, $|S|$ is the state space size, $|A|$ is the action space size, and $\varepsilon$ is the desired imitation gap. MB-TAIL is the first algorithm to achieve this level of expert sample complexity in the unknown transition setting and improves upon the interaction complexity of the best-known algorithm, OAL, by $O(H)$. Additionally, we demonstrate the generalization ability of MB-TAIL by extending it to the function approximation setting and proving that it can achieve expert sample and interaction complexity independent of $|S|$

Fan-Ming Luo, Tian Xu, Xingchen Cao et al.

Learning a precise dynamics model can be crucial for offline reinforcement learning, which, unfortunately, has been found to be quite challenging. Dynamics models that are learned by fitting historical transitions often struggle to generalize to unseen transitions. In this study, we identify a hidden but pivotal factor termed dynamics reward that remains consistent across transitions, offering a pathway to better generalization. Therefore, we propose the idea of reward-consistent dynamics models: any trajectory generated by the dynamics model should maximize the dynamics reward derived from the data. We implement this idea as the MOREC (Model-based Offline reinforcement learning with Reward Consistency) method, which can be seamlessly integrated into previous offline model-based reinforcement learning (MBRL) methods. MOREC learns a generalizable dynamics reward function from offline data, which is subsequently employed as a transition filter in any offline MBRL method: when generating transitions, the dynamics model generates a batch of transitions and selects the one with the highest dynamics reward value. On a synthetic task, we visualize that MOREC has a strong generalization ability and can surprisingly recover some distant unseen transitions. On 21 offline tasks in D4RL and NeoRL benchmarks, MOREC improves the previous state-of-the-art performance by a significant margin, i.e., 4.6% on D4RL tasks and 25.9% on NeoRL tasks. Notably, MOREC is the first method that can achieve above 95% online RL performance in 6 out of 12 D4RL tasks and 3 out of 9 NeoRL tasks.

Chengxing Jia, Hao Yin, Chenxiao Gao et al.

Model-based offline optimization with dynamics-aware policy provides a new perspective for policy learning and out-of-distribution generalization, where the learned policy could adapt to different dynamics enumerated at the training stage. But due to the limitation under the offline setting, the learned model could not mimic real dynamics well enough to support reliable out-of-distribution exploration, which still hinders policy to generalize well. To narrow the gap, previous works roughly ensemble randomly initialized models to better approximate the real dynamics. However, such practice is costly and inefficient, and provides no guarantee on how well the real dynamics could be approximated by the learned models, which we name coverability in this paper. We actively address this issue by generating models with provable ability to cover real dynamics in an efficient and controllable way. To that end, we design a distance metric for dynamic models based on the occupancy of policies under the dynamics, and propose an algorithm to generate models optimizing their coverage for the real dynamics. We give a theoretical analysis on the model generation process and proves that our algorithm could provide enhanced coverability. As a downstream task, we train a dynamics-aware policy with minor or no conservative penalty, and experiments demonstrate that our algorithm outperforms prior offline methods on existing offline RL benchmarks. We also discover that policies learned by our method have better zero-shot transfer performance, implying their better generalization.

Ziniu Li, Tian Xu, Yang Yu et al.

Behavioral cloning (BC) can recover a good policy from abundant expert data, but may fail when expert data is insufficient. This paper considers a situation where, besides the small amount of expert data, a supplementary dataset is available, which can be collected cheaply from sub-optimal policies. Imitation learning with a supplementary dataset is an emergent practical framework, but its theoretical foundation remains under-developed. To advance understanding, we first investigate a direct extension of BC, called NBCU, that learns from the union of all available data. Our analysis shows that, although NBCU suffers an imitation gap that is larger than BC in the worst case, there exist special cases where NBCU performs better than or equally well as BC. This discovery implies that noisy data can also be helpful if utilized elaborately. Therefore, we further introduce a discriminator-based importance sampling technique to re-weight the supplementary data, proposing the WBCU method. With our newly developed landscape-based analysis, we prove that WBCU can outperform BC in mild conditions. Empirical studies show that WBCU simultaneously achieves the best performance on two challenging tasks where prior state-of-the-art methods fail.

Ruo-Tong Chen, Ke Xue, Chengrui Gao et al.

Chip placement is a critical step in physical design. While reinforcement learning (RL)-based methods have recently emerged, their training primarily focuses on wirelength optimization, and therefore often fail to achieve expert-quality layouts. We identify the reward design as the primary cause for the performance gap with experts, and instead of formalizing intricate processes, we circumvent this by directly learning from expert layouts to derive a reward model. Our approach starts from the final expert layouts to infer step-by-step expert trajectories. Using these trajectories as demonstrations or preferences, we train a model that captures the latent implicit rewards in expert results. Experiments show that our framework can efficiently learn from even a single design and generalize well to unseen cases.

Ludi Li, Junbin Mao, Hanhe Lin et al.

Multi-pulse magnetic resonance imaging (MRI) is widely utilized for clinical practice such as Alzheimer's disease diagnosis. To train a robust model for multi-pulse MRI classification, it requires large and diverse data from various medical institutions while protecting privacy by preventing raw data sharing across institutions. Although federated learning (FL) is a feasible solution to address this issue, it poses challenges of model convergence due to the effect of data heterogeneity and substantial communication overhead due to large numbers of parameters transmitted within the model. To address these challenges, we propose CEPerFed, a communication-efficient personalized FL method. It mitigates the effect of data heterogeneity by incorporating client-side historical risk gradients and historical mean gradients to coordinate local and global optimization. The former is used to weight the contributions from other clients, enhancing the reliability of local updates, while the latter enforces consistency between local updates and the global optimization direction to ensure stable convergence across heterogeneous data distributions. To address the high communication overhead, we propose a hierarchical SVD (HSVD) strategy that transmits only the most critical information required for model updates. Experiments on five classification tasks demonstrate the effectiveness of the CEPerFed method. The code will be released upon acceptance at https://github.com/LD0416/CEPerFed.

Zijie Yang, Yongjing Yin, Chaojun Kong et al.

Natural Medicinal Materials (NMMs) have a long history of global clinical applications and a wealth of records and knowledge. Although NMMs are a major source for drug discovery and clinical application, the utilization and sharing of NMM knowledge face crucial challenges, including the standardized description of critical information, efficient curation and acquisition, and language barriers. To address these, we developed ShennongAlpha, an AI-driven sharing and collaboration platform for intelligent knowledge curation, acquisition, and translation. For standardized knowledge curation, the platform introduced a Systematic Nomenclature to enable accurate differentiation and identification of NMMs. More than fourteen thousand Chinese NMMs have been curated into the platform along with their knowledge. Furthermore, the platform pioneered chat-based knowledge acquisition, standardized machine translation, and collaborative knowledge updating. Together, our study represents the first major advance in leveraging AI to empower NMM knowledge sharing, which not only marks a novel application of AI for Science, but also will significantly benefit the global biomedical, pharmaceutical, physician, and patient communities.

Tian Xu, Zhilong Zhang, Ruishuo Chen et al.

As a prominent category of imitation learning methods, adversarial imitation learning (AIL) has garnered significant practical success powered by neural network approximation. However, existing theoretical studies on AIL are primarily limited to simplified scenarios such as tabular and linear function approximation and involve complex algorithmic designs that hinder practical implementation, highlighting a gap between theory and practice. In this paper, we explore the theoretical underpinnings of online AIL with general function approximation. We introduce a new method called optimization-based AIL (OPT-AIL), which centers on performing online optimization for reward functions and optimism-regularized Bellman error minimization for Q-value functions. Theoretically, we prove that OPT-AIL achieves polynomial expert sample complexity and interaction complexity for learning near-expert policies. To our best knowledge, OPT-AIL is the first provably efficient AIL method with general function approximation. Practically, OPT-AIL only requires the approximate optimization of two objectives, thereby facilitating practical implementation. Empirical studies demonstrate that OPT-AIL outperforms previous state-of-the-art deep AIL methods in several challenging tasks.

Ziniu Li, Tian Xu, Yang Yu et al.

Since the introduction of GAIL, adversarial imitation learning (AIL) methods attract lots of research interests. Among these methods, ValueDice has achieved significant improvements: it beats the classical approach Behavioral Cloning (BC) under the offline setting, and it requires fewer interactions than GAIL under the online setting. Are these improvements benefited from more advanced algorithm designs? We answer this question by the following conclusions. First, we show that ValueDice could reduce to BC under the offline setting. Second, we verify that overfitting exists and regularization matters in the low-data regime. Specifically, we demonstrate that with weight decay, BC also nearly matches the expert performance as ValueDice does. The first two claims explain the superior offline performance of ValueDice. Third, we establish that ValueDice does not work when the expert trajectory is subsampled. Instead, the mentioned success of ValueDice holds when the expert trajectory is complete, in which ValueDice is closely related to BC that performs well as mentioned. Finally, we discuss the implications of our research for imitation learning studies beyond ValueDice.

Jian Liang, Fangrui Lv, Di Liu et al.

In this paper, we focus on learning effective entity matching models over multi-source large-scale data. For real applications, we relax typical assumptions that data distributions/spaces, or entity identities are shared between sources, and propose a Relaxed Multi-source Large-scale Entity-matching (RMLE) problem. Challenges of the problem include 1) how to align large-scale entities between sources to share information and 2) how to mitigate negative transfer from joint learning multi-source data. What's worse, one practical issue is the entanglement between both challenges. Specifically, incorrect alignments may increase negative transfer; while mitigating negative transfer for one source may result in poorly learned representations for other sources and then decrease alignment accuracy. To handle the entangled challenges, we point out that the key is to optimize information sharing first based on Pareto front optimization, by showing that information sharing significantly influences the Pareto front which depicts lower bounds of negative transfer. Consequently, we proposed an Incentive Compatible Pareto Alignment (ICPA) method to first optimize cross-source alignments based on Pareto front optimization, then mitigate negative transfer constrained on the optimized alignments. This mechanism renders each source can learn based on its true preference without worrying about deteriorating representations of other sources. Specifically, the Pareto front optimization encourages minimizing lower bounds of negative transfer, which optimizes whether and which to align. Comprehensive empirical evaluation results on four large-scale datasets are provided to demonstrate the effectiveness and superiority of ICPA. Online A/B test results at a search advertising platform also demonstrate the effectiveness of ICPA in production environments.

Tian Xu, Ziniu Li, Yang Yu et al.

Despite massive empirical evaluations, one of the fundamental questions in imitation learning is still not fully settled: does AIL (adversarial imitation learning) provably generalize better than BC (behavioral cloning)? We study this open problem with tabular and episodic MDPs. For vanilla AIL that uses the direct maximum likelihood estimation, we provide both negative and positive answers under the known transition setting. For some MDPs, we show that vanilla AIL has a worse sample complexity than BC. The key insight is that the state-action distribution matching principle is weak so that AIL may generalize poorly even on visited states from the expert demonstrations. For another class of MDPs, vanilla AIL is proved to generalize well even on non-visited states. Interestingly, its sample complexity is horizon-free, which provably beats BC by a wide margin. Finally, we establish a framework in the unknown transition scenario, which allows AIL to explore via reward-free exploration strategies. Compared with the best-known online apprenticeship learning algorithm, the resulting algorithm improves the sample complexity and interaction complexity.

Tian Xu, Jennifer White, Sinan Kalkan et al.

Recognition of expressions of emotions and affect from facial images is a well-studied research problem in the fields of affective computing and computer vision with a large number of datasets available containing facial images and corresponding expression labels. However, virtually none of these datasets have been acquired with consideration of fair distribution across the human population. Therefore, in this work, we undertake a systematic investigation of bias and fairness in facial expression recognition by comparing three different approaches, namely a baseline, an attribute-aware and a disentangled approach, on two well-known datasets, RAF-DB and CelebA. Our results indicate that: (i) data augmentation improves the accuracy of the baseline model, but this alone is unable to mitigate the bias effect; (ii) both the attribute-aware and the disentangled approaches fortified with data augmentation perform better than the baseline approach in terms of accuracy and fairness; (iii) the disentangled approach is the best for mitigating demographic bias; and (iv) the bias mitigation strategies are more suitable in the existence of uneven attribute distribution or imbalanced number of subgroup data.