Yu Luo

Tianying Ji, Yu Luo, Fuchun Sun et al.

Learning high-quality $Q$-value functions plays a key role in the success of many modern off-policy deep reinforcement learning (RL) algorithms. Previous works primarily focus on addressing the value overestimation issue, an outcome of adopting function approximators and off-policy learning. Deviating from the common viewpoint, we observe that $Q$-values are often underestimated in the latter stage of the RL training process, potentially hindering policy learning and reducing sample efficiency. We find that such a long-neglected phenomenon is often related to the use of inferior actions from the current policy in Bellman updates as compared to the more optimal action samples in the replay buffer. To address this issue, our insight is to incorporate sufficient exploitation of past successes while maintaining exploration optimism. We propose the Blended Exploitation and Exploration (BEE) operator, a simple yet effective approach that updates $Q$-value using both historical best-performing actions and the current policy. Based on BEE, the resulting practical algorithm BAC outperforms state-of-the-art methods in over 50 continuous control tasks and achieves strong performance in failure-prone scenarios and real-world robot tasks. Benchmark results and videos are available at https://jity16.github.io/BEE/.

Tianying Ji, Yu Luo, Fuchun Sun et al.

Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding algorithms are prone to degrade performance by drastic model updating. In this work, we first propose a novel and general theoretical scheme for a non-decreasing performance guarantee of MBRL. Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. These discoveries encourage us to formulate a constrained lower-bound optimization problem to permit the monotonicity of MBRL. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns. Motivated by these analyses, we design a simple but effective algorithm CMLO (Constrained Model-shift Lower-bound Optimization), by introducing an event-triggered mechanism that flexibly determines when to update the model. Experiments show that CMLO surpasses other state-of-the-art methods and produces a boost when various policy optimization methods are employed.

Xinyu Zuo, Haijin Liang, Ning Jing et al. · pku

Fine-grained entity typing (FET) aims to deduce specific semantic types of the entity mentions in text. Modern methods for FET mainly focus on learning what a certain type looks like. And few works directly model the type differences, that is, let models know the extent that one type is different from others. To alleviate this problem, we propose a type-enriched hierarchical contrastive strategy for FET. Our method can directly model the differences between hierarchical types and improve the ability to distinguish multi-grained similar types. On the one hand, we embed type into entity contexts to make type information directly perceptible. On the other hand, we design a constrained contrastive strategy on the hierarchical structure to directly model the type differences, which can simultaneously perceive the distinguishability between types at different granularity. Experimental results on three benchmarks, BBN, OntoNotes, and FIGER show that our method achieves significant performance on FET by effectively modeling type differences.

Shuangping Huang, Yu Luo, Zhenzhou Zhuang et al.

Despite the success of deep neural network (DNN) on sequential data (i.e., scene text and speech) recognition, it suffers from the over-confidence problem mainly due to overfitting in training with the cross-entropy loss, which may make the decision-making less reliable. Confidence calibration has been recently proposed as one effective solution to this problem. Nevertheless, the majority of existing confidence calibration methods aims at non-sequential data, which is limited if directly applied to sequential data since the intrinsic contextual dependency in sequences or the class-specific statistical prior is seldom exploited. To the end, we propose a Context-Aware Selective Label Smoothing (CASLS) method for calibrating sequential data. The proposed CASLS fully leverages the contextual dependency in sequences to construct confusion matrices of contextual prediction statistics over different classes. Class-specific error rates are then used to adjust the weights of smoothing strength in order to achieve adaptive calibration. Experimental results on sequence recognition tasks, including scene text recognition and speech recognition, demonstrate that our method can achieve the state-of-the-art performance.

Bingning Wang, Feiyang Lv, Ting Yao et al.

Visual question answering is an important task in both natural language and vision understanding. However, in most of the public visual question answering datasets such as VQA, CLEVR, the questions are human generated that specific to the given image, such as `What color are her eyes?'. The human generated crowdsourcing questions are relatively simple and sometimes have the bias toward certain entities or attributes. In this paper, we introduce a new question answering dataset based on image-ChiQA. It contains the real-world queries issued by internet users, combined with several related open-domain images. The system should determine whether the image could answer the question or not. Different from previous VQA datasets, the questions are real-world image-independent queries that are more various and unbiased. Compared with previous image-retrieval or image-caption datasets, the ChiQA not only measures the relatedness but also measures the answerability, which demands more fine-grained vision and language reasoning. ChiQA contains more than 40K questions and more than 200K question-images pairs. A three-level 2/1/0 label is assigned to each pair indicating perfect answer, partially answer and irrelevant. Data analysis shows ChiQA requires a deep understanding of both language and vision, including grounding, comparisons, and reading. We evaluate several state-of-the-art visual-language models such as ALBEF, demonstrating that there is still a large room for improvements on ChiQA.

Kexin Zheng, Lauriane Teyssier, Yinan Zheng et al.

The recent development of zero-shot reinforcement learning (RL) has opened a new avenue for learning pre-trained generalist policies that can adapt to arbitrary new tasks in a zero-shot manner. While the popular Forward-Backward representations (FB) and related methods have shown promise in zero-shot RL, we empirically found that their modeling lacks expressivity and that extrapolation errors caused by out-of-distribution (OOD) actions during offline learning sometimes lead to biased representations, ultimately resulting in suboptimal performance. To address these issues, we propose Behavior-REgularizEd Zero-shot RL with Expressivity enhancement (BREEZE), an upgraded FB-based framework that simultaneously enhances learning stability, policy extraction capability, and representation learning quality. BREEZE introduces behavioral regularization in zero-shot RL policy learning, transforming policy optimization into a stable in-sample learning paradigm. Additionally, BREEZE extracts the policy using a task-conditioned diffusion model, enabling the generation of high-quality and multimodal action distributions in zero-shot RL settings. Moreover, BREEZE employs expressive attention-based architectures for representation modeling to capture the complex relationships between environmental dynamics. Extensive experiments on ExORL and D4RL Kitchen demonstrate that BREEZE achieves the best or near-the-best performance while exhibiting superior robustness compared to prior offline zero-shot RL methods. The official implementation is available at: https://github.com/Whiterrrrr/BREEZE.

Zhenghua Peng, Yu Luo, Tianshui Chen et al.

Deep sequence recognition (DSR) models receive increasing attention due to their superior application to various applications. Most DSR models use merely the target sequences as supervision without considering other related sequences, leading to over-confidence in their predictions. The DSR models trained with label smoothing regularize labels by equally and independently smoothing each token, reallocating a small value to other tokens for mitigating overconfidence. However, they do not consider tokens/sequences correlations that may provide more effective information to regularize training and thus lead to sub-optimal performance. In this work, we find tokens/sequences with high perception and semantic correlations with the target ones contain more correlated and effective information and thus facilitate more effective regularization. To this end, we propose a Perception and Semantic aware Sequence Regularization framework, which explore perceptively and semantically correlated tokens/sequences as regularization. Specifically, we introduce a semantic context-free recognition and a language model to acquire similar sequences with high perceptive similarities and semantic correlation, respectively. Moreover, over-confidence degree varies across samples according to their difficulties. Thus, we further design an adaptive calibration intensity module to compute a difficulty score for each samples to obtain finer-grained regularization. Extensive experiments on canonical sequence recognition tasks, including scene text and speech recognition, demonstrate that our method sets novel state-of-the-art results. Code is available at https://github.com/husterpzh/PSSR.

Tianying Ji, Yongyuan Liang, Yan Zeng et al. · tsinghua

The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms. Leveraging this insight, we explore the causal relationship between different action dimensions and rewards to evaluate the significance of various primitive behaviors during training. We introduce a causality-aware entropy term that effectively identifies and prioritizes actions with high potential impacts for efficient exploration. Furthermore, to prevent excessive focus on specific primitive behaviors, we analyze the gradient dormancy phenomenon and introduce a dormancy-guided reset mechanism to further enhance the efficacy of our method. Our proposed algorithm, ACE: Off-policy Actor-critic with Causality-aware Entropy regularization, demonstrates a substantial performance advantage across 29 diverse continuous control tasks spanning 7 domains compared to model-free RL baselines, which underscores the effectiveness, versatility, and efficient sample efficiency of our approach. Benchmark results and videos are available at https://ace-rl.github.io/.

Lei Lv, Yunfei Li, Yu Luo et al.

We present \textbf{FlowRL}, a novel framework for online reinforcement learning that integrates flow-based policy representation with Wasserstein-2-regularized optimization. We argue that in addition to training signals, enhancing the expressiveness of the policy class is crucial for the performance gains in RL. Flow-based generative models offer such potential, excelling at capturing complex, multimodal action distributions. However, their direct application in online RL is challenging due to a fundamental objective mismatch: standard flow training optimizes for static data imitation, while RL requires value-based policy optimization through a dynamic buffer, leading to difficult optimization landscapes. FlowRL first models policies via a state-dependent velocity field, generating actions through deterministic ODE integration from noise. We derive a constrained policy search objective that jointly maximizes Q through the flow policy while bounding the Wasserstein-2 distance to a behavior-optimal policy implicitly derived from the replay buffer. This formulation effectively aligns the flow optimization with the RL objective, enabling efficient and value-aware policy learning despite the complexity of the policy class. Empirical evaluations on DMControl and Humanoidbench demonstrate that FlowRL achieves competitive performance in online reinforcement learning benchmarks.

Yu Luo, Fuchun Sun, Tianying Ji et al.

Hierarchical reinforcement learning (HRL) addresses complex long-horizon tasks by skillfully decomposing them into subgoals. Therefore, the effectiveness of HRL is greatly influenced by subgoal reachability. Typical HRL methods only consider subgoal reachability from the unilateral level, where a dominant level enforces compliance to the subordinate level. However, we observe that when the dominant level becomes trapped in local exploration or generates unattainable subgoals, the subordinate level is negatively affected and cannot follow the dominant level's actions. This can potentially make both levels stuck in local optima, ultimately hindering subsequent subgoal reachability. Allowing real-time bilateral information sharing and error correction would be a natural cure for this issue, which motivates us to propose a mutual response mechanism. Based on this, we propose the Bidirectional-reachable Hierarchical Policy Optimization (BrHPO)--a simple yet effective algorithm that also enjoys computation efficiency. Experiment results on a variety of long-horizon tasks showcase that BrHPO outperforms other state-of-the-art HRL baselines, coupled with a significantly higher exploration efficiency and robustness.

Yu Luo, Mingxuan Jing, Tianying Ji et al.

Model Predictive Control (MPC) has shown the great performance of target optimization and constraint satisfaction. However, the heavy computation of the Optimal Control Problem (OCP) at each triggering instant brings the serious delay from state sampling to the control signals, which limits the applications of MPC in resource-limited robot manipulator systems over complicated tasks. In this paper, we propose a novel robust tube-based smooth-MPC strategy for nonlinear robot manipulator planning systems with disturbances and constraints. Based on piecewise linearization and state prediction, our control strategy improves the smoothness and optimizes the delay of the control process. By deducing the deviation of the real system states and the nominal system states, we can predict the next real state set at the current instant. And by using this state set as the initial condition, we can solve the next OCP ahead and store the optimal controls based on the nominal system states, which eliminates the delay. Furthermore, we linearize the nonlinear system with a given upper bound of error, reducing the complexity of the OCP and improving the response speed. Based on the theoretical framework of tube MPC, we prove that the control strategy is recursively feasible and closed-loop stable with the constraints and disturbances. Numerical simulations have verified the efficacy of the designed approach compared with the conventional MPC.

Xin Ma, Zhicheng Zhang, Danfeng Wang et al.

In deep learning-based local stereo matching methods, larger image patches usually bring better stereo matching accuracy. However, it is unrealistic to increase the size of the image patch size without restriction. Arbitrarily extending the patch size will change the local stereo matching method into the global stereo matching method, and the matching accuracy will be saturated. We simplified the existing Siamese convolutional network by reducing the number of network parameters and propose an efficient CNN based structure, namely Adaptive Deconvolution-based disparity matching Net (ADSM net) by adding deconvolution layers to learn how to enlarge the size of input feature map for the following convolution layers. Experimental results on the KITTI 2012 and 2015 datasets demonstrate that the proposed method can achieve a good trade-off between accuracy and complexity.