arXiv subjects

Qiang Fu

Publications and source records attributed to Qiang Fu.

At least 145 records · Page 8Linked to original sources

arXiv2021

Learning Diverse Policies in MOBA Games via Macro-Goals

Recently, many researchers have made successful progress in building the AI systems for MOBA-game-playing with deep reinforcement learning, such as on Dota 2 and Honor of Kings. Even though these AI systems have achieved or even exceeded human-level performance, they still suffer from the lack of policy diversity. In this paper, we propose a novel Macro-Goals Guided framework, called MGG, to learn diverse policies in MOBA games. MGG abstracts strategies as macro-goals from human demonstrations and trains a Meta-Controller to predict these macro-goals. To enhance policy diversity, MGG samples macro-goals from the Meta-Controller prediction and guides the training process towards these goals. Experimental results on the typical MOBA game Honor of Kings demonstrate that MGG can execute diverse policies in different matches and lineups, and also outperform the state-of-the-art methods over 102 heroes.

cs.LG↗

arXiv2021

NN3A: Neural Network supported Acoustic Echo Cancellation, Noise Suppression and Automatic Gain Control for Real-Time Communications

Acoustic echo cancellation (AEC), noise suppression (NS) and automatic gain control (AGC) are three often required modules for real-time communications (RTC). This paper proposes a neural network supported algorithm for RTC, namely NN3A, which incorporates an adaptive filter and a multi-task model for residual echo suppression, noise reduction and near-end speech activity detection. The proposed algorithm is shown to outperform both a method using separate models and an end-to-end alternative. It is further shown that there exists a trade-off in the model between residual suppression and near-end speech distortion, which could be balanced by a novel loss weighting function. Several practical aspects of training the joint model are also investigated to push its performance to limit.

cs.SD↗

arXiv2021

Controllable Multichannel Speech Dereverberation based on Deep Neural Networks

Neural network based speech dereverberation has achieved promising results in recent studies. Nevertheless, many are focused on recovery of only the direct path sound and early reflections, which could be beneficial to speech perception, are discarded. The performance of a model trained to recover clean speech degrades when evaluated on early reverberation targets, and vice versa. This paper proposes a novel deep neural network based multichannel speech dereverberation algorithm, in which the dereverberation level is controllable. This is realized by adding a simple floating-point number as target controller of the model. Experiments are conducted using spatially distributed microphones, and the efficacy of the proposed algorithm is confirmed in various simulated conditions.

cs.SD↗

arXiv2021

Neuron Campaign for Initialization Guided by Information Bottleneck Theory

Initialization plays a critical role in the training of deep neural networks (DNN). Existing initialization strategies mainly focus on stabilizing the training process to mitigate gradient vanish/explosion problems. However, these initialization methods are lacking in consideration about how to enhance generalization ability. The Information Bottleneck (IB) theory is a well-known understanding framework to provide an explanation about the generalization of DNN. Guided by the insights provided by IB theory, we design two criteria for better initializing DNN. And we further design a neuron campaign initialization algorithm to efficiently select a good initialization for a neural network on a given dataset. The experiments on MNIST dataset show that our method can lead to a better generalization performance with faster convergence.

cs.LG↗

arXiv2021

Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search

Hero drafting is essential in MOBA game playing as it builds the team of each side and directly affects the match outcome. State-of-the-art drafting methods fail to consider: 1) drafting efficiency when the hero pool is expanded; 2) the multi-round nature of a MOBA 5v5 match series, i.e., two teams play best-of-N and the same hero is only allowed to be drafted once throughout the series. In this paper, we formulate the drafting process as a multi-round combinatorial game and propose a novel drafting algorithm based on neural networks and Monte-Carlo tree search, named JueWuDraft. Specifically, we design a long-term value estimation mechanism to handle the best-of-N drafting case. Taking Honor of Kings, one of the most popular MOBA games at present, as a running case, we demonstrate the practicality and effectiveness of JueWuDraft when compared to state-of-the-art drafting methods.

cs.AI↗

arXiv2021

A Miniature Biological Eagle-Eye Vision System for Small Target Detection

Small target detection is known to be a challenging problem. Inspired by the structural characteristics and physiological mechanism of eagle-eye, a miniature vision system is designed for small target detection in this paper. First, a hardware platform is established, which consists of a pan-tilt, a short-focus camera and a long-focus camera. Then, based on the visual attention mechanism of eagle-eye, the cameras with different focal lengths are controlled cooperatively to achieve small target detection. Experimental results show that the designed biological eagle-eye vision system can accurately detect small targets, which has a strong adaptive ability.

cs.CV↗

arXiv2021

Vision-Based Target Localization for a Flapping-Wing Aerial Vehicle

The flapping-wing aerial vehicle (FWAV) is a new type of flying robot that mimics the flight mode of birds and insects. However, FWAVs have their special characteristics of less load capacity and short endurance time, so that most existing systems of ground target localization are not suitable for them. In this paper, a vision-based target localization algorithm is proposed for FWAVs based on a generic camera model. Since sensors exist measurement error and the camera exists jitter and motion blur during flight, Gaussian noises are introduced in the simulation experiment, and then a first-order low-pass filter is used to stabilize the localization values. Moreover, in order to verify the feasibility and accuracy of the target localization algorithm, we design a set of simulation experiments where various noises are added. From the simulation results, it is found that the target localization algorithm has a good performance.

cs.RO↗

arXiv2021

Active-set algorithms based statistical inference for shape-restricted generalized additive Cox regression models

Recently the shape-restricted inference has gained popularity in statistical and econometric literature in order to relax the linear or quadratic covariate effect in regression analyses. The typical shape-restricted covariate effect includes monotonic increasing, decreasing, convexity or concavity. In this paper, we introduce the shape-restricted inference to the celebrated Cox regression model (SR-Cox), in which the covariate response is modeled as shape-restricted additive functions. The SR-Cox regression approximates the shape-restricted functions using a spline basis expansion with data driven choice of knots. The underlying minimization of negative log-likelihood function is formulated as a convex optimization problem, which is solved with an active-set optimization algorithm. The highlight of this algorithm is that it eliminates the superfluous knots automatically. When covariate effects include combinations of convex or concave terms with unknown forms and linear terms, the most interesting finding is that SR-Cox produces accurate linear covariate effect estimates which are comparable to the maximum partial likelihood estimates if indeed the forms are known. We conclude that concave or convex SR-Cox models could significantly improve nonlinear covariate response recovery and model goodness of fit.

stat.ME↗

arXiv2021

Boosting Offline Reinforcement Learning with Residual Generative Modeling

Offline reinforcement learning (RL) tries to learn the near-optimal policy with recorded offline experience without online exploration. Current offline RL research includes: 1) generative modeling, i.e., approximating a policy using fixed data; and 2) learning the state-action value function. While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected. In this paper, we analyze the error in generative modeling. We propose AQL (action-conditioned Q-learning), a residual generative model to reduce policy approximation error for offline RL. We show that our method can learn more accurate policy approximations in different benchmark datasets. In addition, we show that the proposed offline RL method can learn more competitive AI agents in complex control tasks under the multiplayer online battle arena (MOBA) game Honor of Kings.

cs.LG↗

arXiv2021

Single-crystal hexagonal boron nitride monolayer epitaxially grown on Cu (111) thin film across a wafer

We demonstrate single crystal growth of wafer-scale hexagonal boron nitride (hBN), an insulating atomic thin monolayer, on high-symmetry index surface plane Cu(111). The unidirectional epitaxial growth is guaranteed by large binding energy difference, ~0.23 eV, between A- and B-steps edges on Cu(111) docking with B6N7 clusters, confirmed by density functional theory calculations.

cond-mat.mtrl-sci↗

arXiv2021

MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks

In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem. In this paper, to enhance the diversity of relabeled goals, we develop FGI (Foresight Goal Inference), a new relabeling strategy that relabels the goals by looking into the future with a learned dynamics model. Besides, to improve sample efficiency, we propose to use the dynamics model to generate simulated trajectories for policy training. By integrating these two improvements, we introduce the MapGo framework (Model-Assisted Policy Optimization for Goal-oriented tasks). In our experiments, we first show the effectiveness of the FGI strategy compared with the hindsight one, and then show that the MapGo framework achieves higher sample efficiency when compared to model-free baselines on a set of complicated tasks.

cs.AI↗

arXiv2021

Joint Online Multichannel Acoustic Echo Cancellation, Speech Dereverberation and Source Separation

This paper presents a joint source separation algorithm that simultaneously reduces acoustic echo, reverberation and interfering sources. Target speeches are separated from the mixture by maximizing independence with respect to the other sources. It is shown that the separation process can be decomposed into cascading sub-processes that separately relate to acoustic echo cancellation, speech dereverberation and source separation, all of which are solved using the auxiliary function based independent component/vector analysis techniques, and their solving orders are exchangeable. The cascaded solution not only leads to lower computational complexity but also better separation performance than the vanilla joint algorithm.

cs.SD↗

arXiv2021

Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging

We introduce Mask-ToF, a method to reduce flying pixels (FP) in time-of-flight (ToF) depth captures. FPs are pervasive artifacts which occur around depth edges, where light paths from both an object and its background are integrated over the aperture. This light mixes at a sensor pixel to produce erroneous depth estimates, which can adversely affect downstream 3D vision tasks. Mask-ToF starts at the source of these FPs, learning a microlens-level occlusion mask which effectively creates a custom-shaped sub-aperture for each sensor pixel. This modulates the selection of foreground and background light mixtures on a per-pixel basis and thereby encodes scene geometric information directly into the ToF measurements. We develop a differentiable ToF simulator to jointly train a convolutional neural network to decode this information and produce high-fidelity, low-FP depth reconstructions. We test the effectiveness of Mask-ToF on a simulated light field dataset and validate the method with an experimental prototype. To this end, we manufacture the learned amplitude mask and design an optical relay system to virtually place it on a high-resolution ToF sensor. We find that Mask-ToF generalizes well to real data without retraining, cutting FP counts in half.

eess.IV↗

arXiv2021

Weighted Recursive Least Square Filter and Neural Network based Residual Echo Suppression for the AEC-Challenge

This paper presents a real-time Acoustic Echo Cancellation (AEC) algorithm submitted to the AEC-Challenge. The algorithm consists of three modules: Generalized Cross-Correlation with PHAse Transform (GCC-PHAT) based time delay compensation, weighted Recursive Least Square (wRLS) based linear adaptive filtering and neural network based residual echo suppression. The wRLS filter is derived from a novel semi-blind source separation perspective. The neural network model predicts a Phase-Sensitive Mask (PSM) based on the aligned reference and the linear filter output. The algorithm achieved a mean subjective score of 4.00 and ranked 2nd in the AEC-Challenge.

cs.SD↗

arXiv2021

Multi-Agent Deep Reinforcement Learning for Request Dispatching in Distributed-Controller Software-Defined Networking

Recently, distributed controller architectures have been quickly gaining popularity in Software-Defined Networking (SDN). However, the use of distributed controllers introduces a new and important Request Dispatching (RD) problem with the goal for every SDN switch to properly dispatch their requests among all controllers so as to optimize network performance. This goal can be fulfilled by designing an RD policy to guide distribution of requests at each switch. In this paper, we propose a Multi-Agent Deep Reinforcement Learning (MA-DRL) approach to automatically design RD policies with high adaptability and performance. This is achieved through a new problem formulation in the form of a Multi-Agent Markov Decision Process (MA-MDP), a new adaptive RD policy design and a new MA-DRL algorithm called MA-PPO. Extensive simulation studies show that our MA-DRL technique can effectively train RD policies to significantly outperform man-made policies, model-based policies, as well as RD policies learned via single-agent DRL algorithms.

cs.NI↗

arXiv2020

Towards Playing Full MOBA Games with Deep Reinforcement Learning

MOBA games, e.g., Honor of Kings, League of Legends, and Dota 2, pose grand challenges to AI systems such as multi-agent, enormous state-action space, complex action control, etc. Developing AI for playing MOBA games has raised much attention accordingly. However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i.e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes. As a result, full MOBA games without restrictions are far from being mastered by any existing AI system. In this paper, we propose a MOBA AI learning paradigm that methodologically enables playing full MOBA games with deep reinforcement learning. Specifically, we develop a combination of novel and existing learning techniques, including curriculum self-play learning, policy distillation, off-policy adaption, multi-head value estimation, and Monte-Carlo tree-search, in training and playing a large pool of heroes, meanwhile addressing the scalability issue skillfully. Tested on Honor of Kings, a popular MOBA game, we show how to build superhuman AI agents that can defeat top esports players. The superiority of our AI is demonstrated by the first large-scale performance test of MOBA AI agent in the literature.

cs.AI↗

arXiv2020

Optimal Ternary Linear Complementary Dual Codes

Linear complementary dual (LCD) codes introduced by Massey are the codes whose intersections with their dual codes are trivial. It can help to improve the security of the information processed by sensitive devices, especially against side-channel attacks (SCA) and fault invasive attacks. In this paper, By construction of puncturing, extending, shortening and combination codes, many good ternary LCD codes are presented. We give a Table 1 with the values of $d_{LCD}(n,k)$ for length $ n \leq 20$. In addition, Many of these ternary LCD codes given in this paper are optimal which are saturating the lower or upper bound of Grassl's codetable in \cite{Grassl} and some of them are nearly optimal.

cs.IT↗

arXiv2020

Mastering Complex Control in MOBA Games with Deep Reinforcement Learning

We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games. This problem involves far more complicated state and action spaces than those of traditional 1v1 games, such as Go and Atari series, which makes it very difficult to search any policies with human-level performance. In this paper, we present a deep reinforcement learning framework to tackle this problem from the perspectives of both system and algorithm. Our system is of low coupling and high scalability, which enables efficient explorations at large scale. Our algorithm includes several novel strategies, including control dependency decoupling, action mask, target attention, and dual-clip PPO, with which our proposed actor-critic network can be effectively trained in our system. Tested on the MOBA game Honor of Kings, our AI agent, called Tencent Solo, can defeat top professional human players in full 1v1 games.

cs.AI↗