arXiv subjects

Yongyi Wang

Publications and source records attributed to Yongyi Wang.

13 recordsLinked to original sources

arXiv2026

Understanding and Stabilizing Deep Q-Learning via Controlled Bootstrapping and Regulated Value Dynamics

Deep Q-learning (DQL) has achieved remarkable empirical success in reinforcement learning, yet its training process remains notoriously unstable. Existing studies often attribute instability to isolated factors such as overestimation bias or representation learning issues, lacking a unified understanding of how different sources of instability interact during recursive value estimation. In this work, we provide a systematic analysis of instability in deep Q-learning from three complementary perspectives: operator-level bias in Bellman bootstrapping, estimator-level sensitivity of greedy action selection to regression noise, and parameter-dynamics imbalance under aggressive data reuse. We identify a reward-triggered self-reinforcing trap and characteristic parameter spike dynamics, then derive stabilization principles for controlled bootstrapping, ensemble quantile estimation, and spike-based parameter regulation. Experiments on Atari-100K and Procgen demonstrate competitive performance and improved training stability.

cs.LG↗

arXiv2026

Beyond Autoregressive RTG: Conditioning via Injection Outside Sequential Modeling in Decision Transformer

Decision Transformer (DT) formulates offline reinforcement learning as autoregressive sequence modeling, achieving promising results by predicting actions from a sequence of Return-to-Go (RTG), state, and action tokens. However, RTG is a scalar that summarizes future rewards, containing far less information than typical state or action vectors, yet it consumes the same computational budget per token. Worse, the self-attention cost of Transformers grows quadratically with sequence length, so including RTG as a separate token adds unnecessary overhead. We propose SlimDT, which removes RTG from the autoregressive sequence. Instead, we inject RTG information into the state representations before the sequential modeling step, allowing the Transformer to process only a compact (state, action) sequence. This reduces the sequence length by one-third, directly improving inference efficiency. On the D4RL benchmark, SlimDT surpasses standard DT across various tasks and achieves performance comparable to existing state-of-the-art methods. Decoupling a sparse conditioning signal from an information-rich sequence thus yields both computational gains and higher task performance.

cs.LG↗

arXiv2026

ShuttleEnv: An Interactive Data-Driven RL Environment for Badminton Strategy Modeling

We present ShuttleEnv, an interactive and data-driven simulation environment for badminton, designed to support reinforcement learning and strategic behavior analysis in fast-paced adversarial sports. The environment is grounded in elite-player match data and employs explicit probabilistic models to simulate rally-level dynamics, enabling realistic and interpretable agent-opponent interactions without relying on physics-based simulation. In this demonstration, we showcase multiple trained agents within ShuttleEnv and provide live, step-by-step visualization of badminton rallies, allowing attendees to explore different play styles, observe emergent strategies, and interactively analyze decision-making behaviors. ShuttleEnv serves as a reusable platform for research, visualization, and demonstration of intelligent agents in sports AI. Our ShuttleEnv demo video URL: https://drive.google.com/file/d/1hTR4P16U27H2O0-w316bR73pxE2ucczX/view

cs.AI↗

arXiv2026

Percolation and Criticality in Hyperuniform Networks

Hyperuniform many-particle systems, which encompass crystals, quasicrystals and certain exotic disordered systems, exhibit an anomalous suppression of density fluctuations on macroscopic length scales relative to those of conventional disordered systems. Here we investigate the percolation behaviors of disordered stealthy hyperuniform systems (SHU), a subclass of hyperuniform configurations for which the structure factor vanishes for a finite range of wavevectors near the origin, with the degree of stealthiness controlled via a parameter $\chi$. We construct Delaunay triangulation networks derived from SHU configurations with varying $\chi$ as well as Poisson point configurations for the purpose of comparison. We investigate a non-uniform bond percolation process, in which bond occupation probabilities decrease with the Euclidean distance between the connected vertices. In this setting, percolation is induced by varying a tuning parameter $z$. We estimate the percolation thresholds $z_c$ and critical exponents of the networks via finite-size scaling and the Newman-Ziff algorithm. We find that SHU networks exhibit lower percolation thresholds than Poisson networks. Notably, the percolation threshold of SHU networks decreases with the stealthiness parameter $\chi$, indicating that global connectivity emerges more readily as short-range order increases. Moreover, we show that SHU networks with large $\chi$ belong to the same universality class as lattices, while Poisson and low-$\chi$ systems show deviations. We relate the shift in critical exponents to the degree of suppression of density fluctuations in the point configurations. Our work extends previous studies on transport properties of SHU systems from continuum two-phase media to networks. These results open new avenues for optimizing the resilience of statistically homogeneous disordered networks.

cond-mat.stat-mech↗

arXiv2026

Pareto-guided Pipeline for Distilling Featherweight AI Agents in Mobile MOBA Games

Recent advances in game AI have demonstrated the feasibility of training agents that surpass top-tier human professionals in complex environments such as Honor of Kings (HoK), a leading mobile multiplayer online battle arena (MOBA) game. However, deploying such powerful agents on mobile devices remains a major challenge. On one hand, the intricate multi-modal state representation and hierarchical action space of HoK demand large, sophisticated policy networks that are inherently difficult to compress into lightweight forms. On the other hand, production deployment requires high-frequency inference under strict energy and latency constraints on mobile platform. To the best of our knowledge, bridging large-scale game AI and practical on-device deployment has not been systematically studied. In this work, we propose a Pareto optimality guided pipeline and design a high-efficiency student architecture search space tailored for mobile execution, enabling systematic exploration of the trade-off between performance and efficiency. Experimental results demonstrate that the distilled model achieves remarkable efficiency, including an $12.4\times$ faster inference speed (under 0.5ms per frame) and a $15.6\times$ improvement in energy efficiency (under 0.5mAh per game), while retaining a 40.32% win rate against the original teacher model.

cs.LG↗

arXiv2026

Decoupling Return-to-Go for Efficient Decision Transformer

The Decision Transformer (DT) has established a powerful sequence modeling approach to offline reinforcement learning. It conditions its action predictions on Return-to-Go (RTG), using it both to distinguish trajectory quality during training and to guide action generation at inference. In this work, we identify a critical redundancy in this design: feeding the entire sequence of RTGs into the Transformer is theoretically unnecessary, as only the most recent RTG affects action prediction. We show that this redundancy can impair DT's performance through experiments. To resolve this, we propose the Decoupled DT (DDT). DDT simplifies the architecture by processing only observation and action sequences through the Transformer, using the latest RTG to guide the action prediction. This streamlined approach not only improves performance but also reduces computational cost. Our experiments show that DDT significantly outperforms DT and establishes competitive performance against state-of-the-art DT variants across multiple offline RL tasks.

cs.AI↗

arXiv2026

BotzoneBench: Scalable LLM Evaluation via Graded AI Anchors

Large Language Models (LLMs) are increasingly deployed in interactive environments requiring strategic decision-making, yet systematic evaluation of these capabilities remains challenging. Existing benchmarks for LLMs primarily assess static reasoning through isolated tasks and fail to capture dynamic strategic abilities. Recent game-based evaluations employ LLM-vs-LLM tournaments that produce relative rankings dependent on transient model pools, incurring quadratic computational costs and lacking stable performance anchors for longitudinal tracking. The central challenge is establishing a scalable evaluation framework that measures LLM strategic reasoning against consistent, interpretable standards rather than volatile peer models. Here we show that anchoring LLM evaluation to fixed hierarchies of skill-calibrated game Artificial Intelligence (AI) enables linear-time absolute skill measurement with stable cross-temporal interpretability. Built on the Botzone platform's established competitive infrastructure, our BotzoneBench evaluates LLMs across eight diverse games spanning deterministic perfect-information board games to stochastic imperfect-information card games. Through systematic assessment of 177,047 state-action pairs from five flagship models, we reveal significant performance disparities and identify distinct strategic behaviors, with top-performing models achieving proficiency comparable to mid-to-high-tier specialized game AI in multiple domains. This anchored evaluation paradigm generalizes beyond games to any domain with well-defined skill hierarchies, establishing a scalable and reusable framework for assessing interactive AI capabilities.

cs.AI↗

arXiv2026

Mxplainer: Explain and Learn Insights by Imitating Mahjong Agents

People need to internalize the skills of AI agents to improve their own capabilities. Our paper focuses on Mahjong, a multiplayer game involving imperfect information and requiring effective long-term decision-making amidst randomness and hidden information. Through the efforts of AI researchers, several impressive Mahjong AI agents have already achieved performance levels comparable to those of professional human players; however, these agents are often treated as black boxes from which few insights can be gleaned. This paper introduces Mxplainer, a parameterized search algorithm that can be converted into an equivalent neural network to learn the parameters of black-box agents. Experiments on both human and AI agents demonstrate that Mxplainer achieves a top-three action prediction accuracy of over 92% and 90%, respectively, while providing faithful and interpretable approximations that outperform decision-tree methods (34.8% top-three accuracy). This enables Mxplainer to deliver both strategy-level insights into agent characteristics and actionable, step-by-step explanations for individual decisions.

cs.AI↗

arXiv2025

Synthetic POMDPs to Challenge Memory-Augmented RL: Memory Demand Structure Modeling

Recent benchmarks for memory-augmented reinforcement learning (RL) have introduced partially observable Markov decision process (POMDP) environments in which agents must use historical observations to make decisions. However, these benchmarks often lack fine-grained control over the challenges posed to memory models. Synthetic environments offer a solution, enabling precise manipulation of environment dynamics for rigorous and interpretable evaluation of memory-augmented RL. This paper advances the design of such customizable POMDPs with three key contributions: (1) a theoretical framework for analyzing POMDPs based on Memory Demand Structure (MDS) and related concepts; (2) a methodology using linear dynamics, state aggregation, and reward redistribution to construct POMDPs with predefined MDS; and (3) a suite of lightweight, scalable POMDP environments with tunable difficulty, grounded in our theoretical insights. Overall, our work clarifies core challenges in partially observable RL, offers principled guidelines for POMDP design, and aids in selecting and developing suitable memory architectures for RL tasks.

cs.AI↗

arXiv2025

Constructing Non-Markovian Decision Process via History Aggregator

In the domain of algorithmic decision-making, non-Markovian dynamics manifest as a significant impediment, especially for paradigms such as Reinforcement Learning (RL), thereby exerting far-reaching consequences on the advancement and effectiveness of the associated systems. Nevertheless, the existing benchmarks are deficient in comprehensively assessing the capacity of decision algorithms to handle non-Markovian dynamics. To address this deficiency, we have devised a generalized methodology grounded in category theory. Notably, we established the category of Markov Decision Processes (MDP) and the category of non-Markovian Decision Processes (NMDP), and proved the equivalence relationship between them. This theoretical foundation provides a novel perspective for understanding and addressing non-Markovian dynamics. We further introduced non-Markovianity into decision-making problem settings via the History Aggregator for State (HAS). With HAS, we can precisely control the state dependency structure of decision-making problems in the time series. Our analysis demonstrates the effectiveness of our method in representing a broad range of non-Markovian dynamics. This approach facilitates a more rigorous and flexible evaluation of decision algorithms by testing them in problem settings where non-Markovian dynamics are explicitly constructed.

cs.AI↗

arXiv2025

Policy Improvement with Style-Specific Demonstrations

Proficient game agents with diverse play styles enrich the gaming experience and enhance the replay value of games. However, recent advancements in game AI based on reinforcement learning have predominantly focused on improving proficiency, whereas methods based on evolution algorithms generate agents with diverse play styles but exhibit subpar performance compared to RL methods. To address this gap, this paper proposes Mixed Proximal Policy Optimization (MPPO), a method designed to improve the proficiency of existing suboptimal agents while retaining their distinct styles. MPPO unifies loss objectives for both online and offline samples and introduces an implicit constraint to approximate demonstrator policies by adjusting the empirical distribution of samples. Empirical results across environments of varying scales demonstrate that MPPO achieves proficiency levels comparable to, or even superior to, pure online algorithms while preserving demonstrators' play styles. This work presents an effective approach for generating highly proficient and diverse game agents, ultimately contributing to more engaging gameplay experiences.

cs.AI↗

arXiv2025

From Multimodal Perception to Strategic Reasoning: A Survey on AI-Generated Game Commentary

The advent of artificial intelligence has propelled AI-Generated Game Commentary (AI-GGC) into a rapidly expanding research area, offering advantages such as scalable availability and personalized narration. However, existing studies remain fragmented, and a systematic survey that unifies prior efforts is still lacking. To bridge this gap, our survey introduces a unified framework that systematically organizes the AI-GGC landscape. We present a novel taxonomy focused on three core commentator capabilities: Live Observation, Strategic Analysis, and Historical Recall, and further categorize commentary into three corresponding types: Descriptive Commentary, Analytical Commentary, and Background Commentary. Building on this structure, we provide an in-depth review of methods, datasets, and evaluation metrics, analyzing their strengths and limitations. Finally, we highlight key challenges and point out promising directions for future research in AI-GGC.

cs.CL↗

arXiv2023

The relationship between activated H2 bond length and adsorption distance on MXenes identified with graph neural network and resonating valence bond theory

Motivated by the recent experimental study on hydrogen storage in MXene multilayers [Nature Nanotechnol. 2021, 16, 331], for the first time we propose a workflow to computationally screen 23,857 compounds of MXene to explore the general relation between the activated H2 bond length and adsorption distance. By using density functional theory (DFT), we generate a dataset to investigate the adsorption geometries of hydrogen on MXenes, based on which we train physics-informed atomistic line graph neural networks (ALIGNNs) to predict adsorption parameters. To fit the results, we further derived a formula that quantitatively reproduces the dependence of H2 bond length on the adsorption distance from MXenes within the framework of Pauling's resonating valence bond (RVB) theory, revealing the impact of transition metal's ligancy and valence on activating dihydrogen in H2 storage.

cond-mat.mtrl-sci↗