arXiv subjects

Hanyan Huang

Publications and source records attributed to Hanyan Huang.

4 recordsLinked to original sources

arXiv2026

Hypercube Policy Regularization Framework for Offline Reinforcement Learning

Offline reinforcement learning has received extensive attention from scholars because it avoids the interaction between the agent and the environment by learning a policy through a static dataset. However, general reinforcement learning methods cannot get satisfactory results in offline reinforcement learning due to the out-of-distribution state actions that the dataset cannot cover during training. To solve this problem, the policy regularization method that tries to directly clone policies used in static datasets has received numerous studies due to its simplicity and effectiveness. However, policy constraint methods make the agent choose the corresponding actions in the static dataset. This type of constraint is usually over-conservative, which results in suboptimal policies, especially in low-quality static datasets. In this paper, a hypercube policy regularization framework is proposed, this method alleviates the constraints of policy constraint methods by allowing the agent to explore the actions corresponding to similar states in the static dataset, which increases the effectiveness of algorithms in low-quality datasets. It was also theoretically demonstrated that the hypercube policy regularization framework can effectively improve the performance of original algorithms. In addition, the hypercube policy regularization framework is combined with TD3-BC and Diffusion-QL for experiments on D4RL datasets which are called TD3-BC-C and Diffusion-QL-C. The experimental results of the score demonstrate that TD3-BC-C and Diffusion-QL-C perform better than state-of-the-art algorithms like IQL, CQL, TD3-BC and Diffusion-QL in most D4RL environments in approximate time.

cs.LG↗

arXiv2026

CVBench: Benchmarking Cross-Video Synergies for Complex Multimodal Reasoning

While multimodal large language models (MLLMs) exhibit strong performance on single-video tasks (e.g., video question answering), their capability for spatiotemporal pattern reasoning across multiple videos remains a critical gap in pattern recognition research. However, this capability is essential for real-world applications, including multi-camera surveillance and cross-video procedural learning. To bridge this gap, we present CVBench, the first diagnostic benchmark designed to assess cross-video relational reasoning rigorously. CVBench comprises 1,000 question-answer pairs spanning three hierarchical tiers: cross-video object association (identifying shared entities), cross-video event association (linking temporal or causal event chains), and cross-video complex reasoning (integrating commonsense and domain knowledge). Built from five domain-diverse video clusters (e.g., sports, life records), the benchmark challenges models to analyze and integrate spatiotemporal patterns from dynamic visual streams. Extensive evaluation of 10+ leading MLLMs (including GPT-4o, Gemini-2.0-flash, Qwen2.5-VL) under zero-shot or chain-of-thought prompting paradigms. Key findings reveal stark performance gaps: even top models, such as GPT-4o, achieve only 63.5% accuracy on causal reasoning tasks, compared to the 91.3% accuracy of human performance. Crucially, our analysis reveals fundamental bottlenecks inherent in current MLLMs architectures, notably deficient inter-video context retention and poor disambiguation of overlapping entities. CVBench establishes a rigorous framework for advancing pattern recognition methodologies in multi-video scenarios, providing architectural insights for next-generation models. The data and evaluation code are available at: https://github.com/Hokhim2/CVBench.

cs.CV↗

arXiv2024

Grid-Mapping Pseudo-Count Constraint for Offline Reinforcement Learning

Offline reinforcement learning learns from a static dataset without interacting with environments, which ensures security and thus owns a good application prospect. However, directly applying naive reinforcement learning algorithm usually fails in an offline environment due to inaccurate Q value approximation caused by out-of-distribution (OOD) state-actions. It is an effective way to solve this problem by penalizing the Q-value of OOD state-actions. Among the methods of punishing OOD state-actions, count-based methods have achieved good results in discrete domains in a simple form. Inspired by it, a novel pseudo-count method for continuous domains called Grid-Mapping Pseudo-Count method (GPC) is proposed by extending the count-based method from discrete to continuous domains. Firstly, the continuous state and action space are mapped to discrete space using Grid-Mapping, then the Q-values of OOD state-actions are constrained through pseudo-count. Secondly, the theoretical proof is given to show that GPC can obtain appropriate uncertainty constraints under fewer assumptions than other pseudo-count methods. Thirdly, GPC is combined with Soft Actor-Critic algorithm (SAC) to get a new algorithm called GPC-SAC. Lastly, experiments on D4RL datasets are given to show that GPC-SAC has better performance and less computational cost than other algorithms that constrain the Q-value.

cs.LG↗

arXiv2023

A PC-Kriging-HDMR integrated with an adaptive sequential sampling strategy for high-dimensional approximate modeling

High-dimensional complex multi-parameter problems are prevalent in engineering, exceeding the capabilities of traditional surrogate models designed for low/medium-dimensional problems. These models face the curse of dimensionality, resulting in decreased modeling accuracy as the design parameter space expands. Furthermore, the lack of a parameter decoupling mechanism hinders the identification of couplings between design variables, particularly in highly nonlinear cases. To address these challenges and enhance prediction accuracy while reducing sample demand, this paper proposes a PC-Kriging-HDMR approximate modeling method within the framework of Cut-HDMR. The method leverages the precision of PC-Kriging and optimizes test point placement through a multi-stage adaptive sequential sampling strategy. This strategy encompasses a first-stage adaptive proportional sampling criterion and a second-stage central-based maximum entropy criterion. Numerical tests and a practical application involving a cantilever beam demonstrate the advantages of the proposed method. Key findings include: (1) The performance of traditional single-surrogate models, such as Kriging, significantly deteriorates in high-dimensional nonlinear problems compared to combined surrogate models under the Cut-HDMR framework (e.g., Kriging-HDMR, PCE-HDMR, SVR-HDMR, MLS-HDMR, and PC-Kriging-HDMR); (2) The number of samples required for PC-Kriging-HDMR modeling increases polynomially rather than exponentially as the parameter space expands, resulting in substantial computational cost reduction; (3) Among existing Cut-HDMR methods, no single approach outperforms the others in all aspects. However, PC-Kriging-HDMR exhibits improved modeling accuracy and efficiency within the desired improvement range compared to PCE-HDMR and Kriging-HDMR, demonstrating robustness.

stat.ME↗