arXiv subjects

Yongle Luo

Publications and source records attributed to Yongle Luo.

9 recordsLinked to original sources

arXiv2025

F.A.C.U.L.: Language-Based Interaction with AI Companions in Gaming

In cooperative video games, traditional AI companions are deployed to assist players, who control them using hotkeys or command wheels to issue predefined commands such as ``attack'', ``defend'', or ``retreat''. Despite their simplicity, these methods, which lack target specificity, limit players' ability to give complex tactical instructions and hinder immersive gameplay experiences. To address this problem, we propose the FPS AI Companion who Understands Language (F.A.C.U.L.), the first real-time AI system that enables players to communicate and collaborate with AI companions using natural language. By integrating natural language processing with a confidence-based framework, F.A.C.U.L. efficiently decomposes complex commands and interprets player intent. It also employs a dynamic entity retrieval method for environmental awareness, aligning human intentions with decision-making. Unlike traditional rule-based systems, our method supports real-time language interactions, enabling players to issue complex commands such as ``clear the second floor'', ``take cover behind that tree'', or ``retreat to the river''. The system provides real-time behavioral responses and vocal feedback, ensuring seamless tactical collaboration. Using the popular FPS game \textit{Arena Breakout: Infinite} as a case study, we present comparisons demonstrating the efficacy of our approach and discuss the advantages and limitations of AI companions based on real-world user feedback.

cs.HC↗

arXiv2025

Game-Oriented ASR Error Correction via RAG-Enhanced LLM

With the rise of multiplayer online games, real-time voice communication is essential for team coordination. However, general ASR systems struggle with gaming-specific challenges like short phrases, rapid speech, jargon, and noise, leading to frequent errors. To address this, we propose the GO-AEC framework, which integrates large language models, Retrieval-Augmented Generation (RAG), and a data augmentation strategy using LLMs and TTS. GO-AEC includes data augmentation, N-best hypothesis-based correction, and a dynamic game knowledge base. Experiments show GO-AEC reduces character error rate by 6.22% and sentence error rate by 29.71%, significantly improving ASR accuracy in gaming scenarios.

cs.AI↗

arXiv2024

On the lattice of the weak factorization systems on a finite lattice

We consider the lattice of all the weak factorization systems on a given finite lattice. We prove that it is semidistributive, trim and congruence uniform. We deduce a graph theoretical approach to the problem of enumerating transfer systems. As an application we find a lower bound for the number of transfer systems on a boolean lattice.

math.CO↗

arXiv2024

Some properties of congruence lattices of path semigroups

Each quiver corresponds to a path semigroup, and such a path semigroup also corresponds to an associative K-algebra over an algebraically closed field K. Let Q be a quiver and S_Q, KQ be its path semigroup, path algebra, respectively. In this paper, we study some properties of the congruence lattice of S_Q. First, we show that there is a one-to-one correspondence between congruences on S and certain algebraic ideals of KQ. Based on such a description, we consider acyclic quivers and show that the congruence latices of such path semigroups are strong upper semimodular but not necessarily lower semimodular. Moreover, we provide some equivalent conditions for the congruence lattices to be modular and distributive.

math.GR↗

arXiv2023

Distributivity in congruence lattices of graph inverse semigroups

Let Γ be a directed graph and Inv(Γ) be the graph inverse semigroup of Γ. Luo and Wang [7] showed that the congruence lattice C(Inv(Γ)) of any graph inverse semigroup Inv(Γ) is upper semimodular, but not lower semimodular in general. Anagnostopoulou-Merkouri, Mesyan and Mitchell characterized the directed graph Γ for which C(Inv(Γ)) is lower semimodular [2]. In the present paper, we show that the lower semimodularity, modularity and distributivity in the congruence lattice C(Inv(Γ)) of any graph inverse semigroup Inv(Γ) are equivalent.

math.GR↗

arXiv2023

Distributivity in lattices of torsion classes over finite-dimensional algebras

Let $A$ be a basic finite-dimensional algebra and denote by $\operatorname{tors} A$ the collection of all all torsion classes of $A$. It has been proved in \cite{Demonet} that $\operatorname{tors} A$ is always a completely semidistributive lattice. In the present paper, we investigate the distributivity of this lattice and proved that the lattice is distributive if and only if the algebra is the finite direct product of finite-dimensional local algebras.

math.RT↗

arXiv2022

Relay Hindsight Experience Replay: Self-Guided Continual Reinforcement Learning for Sequential Object Manipulation Tasks with Sparse Rewards

Exploration with sparse rewards remains a challenging research problem in reinforcement learning (RL). Especially for sequential object manipulation tasks, the RL agent always receives negative rewards until completing all sub-tasks, which results in low exploration efficiency. To solve these tasks efficiently, we propose a novel self-guided continual RL framework, RelayHER (RHER). RHER first decomposes a sequential task into new sub-tasks with increasing complexity and ensures that the simplest sub-task can be learned quickly by utilizing Hindsight Experience Replay (HER). Secondly, we design a multi-goal & multi-task network to learn these sub-tasks simultaneously. Finally, we propose a Self-Guided Exploration Strategy (SGES). With SGES, the learned sub-task policy will guide the agent to the states that are helpful to learn more complex sub-task with HER. By this self-guided exploration and relay policy learning, RHER can solve these sequential tasks efficiently stage by stage. The experimental results show that RHER significantly outperforms vanilla-HER in sample-efficiency on five singleobject and five complex multi-object manipulation tasks (e.g., Push, Insert, ObstaclePush, Stack, TStack, etc.). The proposed RHER has also been applied to learn a contact-rich push task on a physical robot from scratch, and the success rate reached 10/10 with only 250 episodes.

cs.RO↗

arXiv2020

On lattice of congruences on graph inverse semigroups

Congruences on a graph inverse semigroup were recently described in terms of the underline graph. Based on such descriptions, we show that the lattice of congruences on a graph inverse semigroup is upper semimodular but not lower semimodular.

math.GR↗

arXiv2020

Balance Between Efficient and Effective Learning: Dense2Sparse Reward Shaping for Robot Manipulation with Environment Uncertainty

Efficient and effective learning is one of the ultimate goals of the deep reinforcement learning (DRL), although the compromise has been made in most of the time, especially for the application of robot manipulations. Learning is always expensive for robot manipulation tasks and the learning effectiveness could be affected by the system uncertainty. In order to solve above challenges, in this study, we proposed a simple but powerful reward shaping method, namely Dense2Sparse. It combines the advantage of fast convergence of dense reward and the noise isolation of the sparse reward, to achieve a balance between learning efficiency and effectiveness, which makes it suitable for robot manipulation tasks. We evaluated our Dense2Sparse method with a series of ablation experiments using the state representation model with system uncertainty. The experiment results show that the Dense2Sparse method obtained higher expected reward compared with the ones using standalone dense reward or sparse reward, and it also has a superior tolerance of system uncertainty.

cs.LG↗