K-nearest neighbor (kNN) search is a fundamental operation in various point cloud applications, such as autonomous driving. However, the heavy computational intensity and memory demands of kNN search pose significant challenges for efficient implementation, especially in resource-constrained scenarios. To address these challenges, we propose PICK, a processing-in-memory (PIM) architecture designed to accelerate kNN search in point cloud applications. PICK leverages bit-serial-based PIM (BS-PIM) and customized circuits to efficiently handle key operations of kNN search: distance calculation and top-k selection. The run-time off-chip access is eliminated thanks to the large on-chip memory. For distance calculation, we introduce a bit-width clipping technique to reduce the latency of bit-serial execution with negligible accuracy degradation, providing flexible trade-offs between performance and precision. Besides, we propose a filtering-and-selection strategy that realizes approximately constant time complexity for arbitrary values of k. Furthermore, a two-stage pipeline is implemented to parallelize distance calculation and top-k search, effectively hiding latency and improving throughput. According to our experiments, PICK achieves $4.17 \times$ speedup and a $4.42 \times$ energy saving over the state-of-the-art design.

Reinforcement learning (RL) has shown remarkable success in solving complex decision-making and control tasks. However, many model-free RL algorithms experience performance degradation due to inaccurate value estimation, particularly the overestimation of Q-values, which can lead to suboptimal policies. To address this issue, we previously proposed the Distributional Soft Actor-Critic (DSAC or DSACv1), an off-policy RL algorithm that enhances value estimation accuracy by learning a continuous Gaussian value distribution. Despite its effectiveness, DSACv1 faces challenges such as training instability and sensitivity to reward scaling, caused by high variance in critic gradients due to return randomness. In this paper, we introduce three key refinements to DSACv1 to overcome these limitations and further improve Q-value estimation accuracy: expected value substitution, twin value distribution learning, and variance-based critic gradient adjustment. The enhanced algorithm, termed DSAC with Three refinements (DSAC-T or DSACv2), is systematically evaluated across a diverse set of benchmark tasks. Without the need for task-specific hyperparameter tuning, DSAC-T consistently matches or outperforms leading model-free RL algorithms, including SAC, TD3, DDPG, TRPO, and PPO, in all tested environments. Additionally, DSAC-T ensures a stable learning process and maintains robust performance across varying reward scales. Its effectiveness is further demonstrated through real-world application in controlling a wheeled robot, highlighting its potential for deployment in practical robotic tasks.

Learning multimodal policies is crucial for enhancing exploration in online reinforcement learning (RL), especially in tasks with continuous action spaces and non-convex reward landscapes. While recent diffusion policies show promise, they often suffer from low computational efficiency in online settings. A more training-efficient paradigm involves modeling the policy as a Boltzmann distribution and guiding the action sampling directly with the gradient of the Q-value with respect to the action (proportional to the score function of the policy), such as via Langevin dynamics. However, analysis in this paper reveals that this gradient-guided approach suffers from two critical challenges: sampling instability caused by the widely varying magnitude of action gradients; and mode imbalance, where the sampling process inaccurately represents the weights of different high-value action modes. To address these challenges, this paper introduces three targeted techniques: score normalization and reshaping to stabilize the sampling process, and value-based resampling to correct mode imbalance. These techniques are then integrated into an actor-critic framework, resulting in the Score-Enhanced Actor-Critic (SEAC) algorithm. Simulation and real-world experiments demonstrate that SEAC not only effectively learns multimodal behaviors but also achieves state-of-the-art performance and high computational efficiency compared to prior multimodal RL methods. The code of this paper is available at https://github.com/THUzouwenjun/SEAC.

Reinforcement learning (RL) has proven highly effective in addressing complex decision-making and control tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution with learned mean and variance, which constrains their capability to acquire complex policies. In response to this problem, we propose an online RL algorithm termed diffusion actor-critic with entropy regulator (DACER). This algorithm conceptualizes the reverse process of the diffusion model as a novel policy function and leverages the capability of the diffusion model to fit multimodal distributions, thereby enhancing the representational capacity of the policy. Since the distribution of the diffusion policy lacks an analytical expression, its entropy cannot be determined analytically. To mitigate this, we propose a method to estimate the entropy of the diffusion policy utilizing Gaussian mixture model. Building on the estimated entropy, we can learn a parameter $\alpha$ that modulates the degree of exploration and exploitation. Parameter $\alpha$ will be employed to adaptively regulate the variance of the added noise, which is applied to the action output by the diffusion model. Experimental trials on MuJoCo benchmarks and a multimodal task demonstrate that the DACER algorithm achieves state-of-the-art (SOTA) performance in most MuJoCo control tasks while exhibiting a stronger representational capacity of the diffusion policy.

Failure mode and effect analysis (FMEA) is a potent risk analytical instrument extensively utilized for enhancing systems’ quality. Because the classical FMEA model has some deficiencies, numerous fuzzy set-based enhanced FMEA techniques have been developed to improve risk evaluation results’ reasonability. However, most of them require experts to follow certain associated constraints when expressing preferences; otherwise, their preferences will be invalid, which limits experts’ flexibility. In addition, the previous methods rarely consider the reliability of weight allocation results and the stabilization of risk ranking results. Many previous methods usually emphasize the local difference between assessments of failure modes in calculating objective weights and merely depend on one compromise solution in ranking failure modes, both of which may affect the precision of their results. To overcome these limitations, this study applies T-spherical fuzzy sets, the recent generalization of fuzzy sets without strict constraints, to flexibly characterize experts’ preferences. Subsequently, a divergence-based maximizing deviation method is presented to determine the weights of experts and risk factors. A new consensus feedback mechanism is also introduced to achieve consensus among experts. Furthermore, a T-spherical fuzzy combined compromise solution method is presented to rank failure modes stably. Finally, a case study, sensitivity analysis, and comparisons show that the proposed model is effective and practically suitable.

Abstract Meaning Representation is a sentence-level meaning representation, which abstracts the meaning of sentences into a rooted acyclic directed graph. With the continuous expansion of Chinese AMR corpus, more and more scholars have developed parsing systems to automatically parse sentences into Chinese AMR. However, the current parsers can’t deal with concept alignment and relation alignment, let alone the evaluation methods for AMR parsing. Therefore, to make up for the vacancy of Chinese AMR parsing evaluation methods, based on AMR evaluation metric smatch, we have improved the algorithm of generating triples so that to make it compatible with concept alignment and relation alignment. Finally, we obtain a new integrity metric align-smatch for paring evaluation. A comparative research then was conducted on 20 manually annotated AMR and gold AMR, with the result that align-smatch works well in alignments and more robust in evaluating arcs. We also put forward some fine-grained metric for evaluating concept alignment, relation alignment and implicit concepts, in order to further measure parsers’ performance in subtasks.