Hai Nguyen

Hai Nguyen, Andrea Baisero, Dian Wang et al.

Reinforcement learning in partially observable domains is challenging due to the lack of observable state information. Thankfully, learning offline in a simulator with such state information is often possible. In particular, we propose a method for partially observable reinforcement learning that uses a fully observable policy (which we call a state expert) during offline training to improve online performance. Based on Soft Actor-Critic (SAC), our agent balances performing actions similar to the state expert and getting high returns under partial observability. Our approach can leverage the fully-observable policy for exploration and parts of the domain that are fully observable while still being able to learn under partial observability. On six robotics domains, our method outperforms pure imitation, pure reinforcement learning, the sequential or parallel combination of both types, and a recent state-of-the-art method in the same setting. A successful policy transfer to a physical robot in a manipulation task from pixels shows our approach's practicality in learning interesting policies under partial observability.

Hai Nguyen, Sammie Katt, Yuchen Xiao et al.

Robot learning is often difficult due to the expense of gathering data. The need for large amounts of data can, and should, be tackled with effective algorithms and leveraging expert information on robot dynamics. Bayesian reinforcement learning (BRL), thanks to its sample efficiency and ability to exploit prior knowledge, is uniquely positioned as such a solution method. Unfortunately, the application of BRL has been limited due to the difficulties of representing expert knowledge as well as solving the subsequent inference problem. This paper advances BRL for robotics by proposing a specialized framework for physical systems. In particular, we capture this knowledge in a factored representation, then demonstrate the posterior factorizes in a similar shape, and ultimately formalize the model in a Bayesian framework. We then introduce a sample-based online solution method, based on Monte-Carlo tree search and particle filtering, specialized to solve the resulting model. This approach can, for example, utilize typical low-level robot simulators and handle uncertainty over unknown dynamics of the environment. We empirically demonstrate its efficiency by performing on-robot learning in two human-robot interaction tasks with uncertainty about human behavior, achieving near-optimal performance after only a handful of real-world episodes. A video of learned policies is at https://youtu.be/H9xp60ngOes.

Hai Nguyen, Andrea Baisero, David Klee et al.

Incorporating inductive biases is a promising approach for tackling challenging robot learning domains with sample-efficient solutions. This paper identifies partially observable domains where symmetries can be a useful inductive bias for efficient learning. Specifically, by encoding the equivariance regarding specific group symmetries into the neural networks, our actor-critic reinforcement learning agents can reuse solutions in the past for related scenarios. Consequently, our equivariant agents outperform non-equivariant approaches significantly in terms of sample efficiency and final performance, demonstrated through experiments on a range of robotic tasks in simulation and real hardware.

Minh-Huy Hoang, Long Dinh, Hai Nguyen

In reinforcement learning (RL), sparse rewards can present a significant challenge. Fortunately, expert actions can be utilized to overcome this issue. However, acquiring explicit expert actions can be costly, and expert observations are often more readily available. This paper presents a new approach that uses expert observations for learning in robot manipulation tasks with sparse rewards from pixel observations. Specifically, our technique involves using expert observations as intermediate visual goals for a goal-conditioned RL agent, enabling it to complete a task by successively reaching a series of goals. We demonstrate the efficacy of our method in five challenging block construction tasks in simulation and show that when combined with two state-of-the-art agents, our approach can significantly improve their performance while requiring 4-20 times fewer expert actions during training. Moreover, our method is also superior to a hierarchical baseline.

Thanh Tin Nguyen, Long H. Nguyen, Nhat Truong Pham et al.

This study presents our approach on the automatic Vietnamese image captioning for healthcare domain in text processing tasks of Vietnamese Language and Speech Processing (VLSP) Challenge 2021, as shown in Figure 1. In recent years, image captioning often employs a convolutional neural network-based architecture as an encoder and a long short-term memory (LSTM) as a decoder to generate sentences. These models perform remarkably well in different datasets. Our proposed model also has an encoder and a decoder, but we instead use a Swin Transformer in the encoder, and a LSTM combined with an attention module in the decoder. The study presents our training experiments and techniques used during the competition. Our model achieves a BLEU4 score of 0.293 on the vietCap4H dataset, and the score is ranked the 3$^{rd}$ place on the private leaderboard. Our code can be found at \url{https://git.io/JDdJm}.

Hai Nguyen, Hieu Dao, Hung Nguyen et al.

This study presents high-throughput, real-time multi-agent affective computing framework designed to enhance classroom learning through emotional state monitoring. As large classroom sizes and limited teacher student interaction increasingly challenge educators, there is a growing need for scalable, data-driven tools capable of capturing students' emotional and engagement patterns in real time. The system was evaluated using the Classroom Emotion Dataset, consisting of 1,500 labeled images and 300 classroom detection videos. Tailored for IoT devices, the system addresses load balancing and latency challenges through efficient real-time processing. Field testing was conducted across three educational institutions in a large metropolitan area: a primary school (hereafter school A), a secondary school (school B), and a high school (school C). The system demonstrated robust performance, detecting up to 50 faces at 25 FPS and achieving 88% overall accuracy in classifying classroom engagement states. Implementation results showed positive outcomes, with favorable feedback from students, teachers, and parents regarding improved classroom interaction and teaching adaptation. Key contributions of this research include establishing a practical, IoT-based framework for emotion-aware learning environments and introducing the 'Classroom Emotion Dataset' to facilitate further validation and research.

Zhihan Yang, Hai Nguyen

When the environment is partially observable (PO), a deep reinforcement learning (RL) agent must learn a suitable temporal representation of the entire history in addition to a strategy to control. This problem is not novel, and there have been model-free and model-based algorithms proposed for this problem. However, inspired by recent success in model-free image-based RL, we noticed the absence of a model-free baseline for history-based RL that (1) uses full history and (2) incorporates recent advances in off-policy continuous control. Therefore, we implement recurrent versions of DDPG, TD3, and SAC (RDPG, RTD3, and RSAC) in this work, evaluate them on short-term and long-term PO domains, and investigate key design choices. Our experiments show that RDPG and RTD3 can surprisingly fail on some domains and that RSAC is the most reliable, reaching near-optimal performance on nearly all domains. However, one task that requires systematic exploration still proved to be difficult, even for RSAC. These results show that model-free RL can learn good temporal representation using only reward signals; the primary difficulty seems to be computational cost and exploration. To facilitate future research, we have made our PyTorch implementation publicly available at https://github.com/zhihanyang2022/off-policy-continuous-control.

Tung Vu, Yen Nguyen, Hai Nguyen et al.

Recent advances in voice cloning and text-to-speech synthesis have made partial speech manipulation - where an adversary replaces a few words within an utterance to alter its meaning while preserving the speaker's identity - an increasingly realistic threat. Existing audio deepfake detection benchmarks focus on utterance-level binary classification or single-region tampering, leaving a critical gap in detecting and localizing multiple inpainted segments whose count is unknown a priori. We address this gap with three contributions. First, we introduce MIST (Multiregion Inpainting Speech Tampering), a large-scale multilingual dataset spanning 6 languages with 1-3 independently inpainted word-level segments per utterance, generated via LLM-guided semantic replacement and neural voice cloning, with fake content constituting only 2-7% of each utterance. Second, we propose ISA (Iterative Segment Analysis), a backbone-agnostic framework that performs coarse-to-fine sliding-window classification with gap-tolerant region proposal and boundary refinement to recover all tampered regions without prior knowledge of their count. Third, we define SF1@tau, a segment-level F1 metric based on temporal IoU matching that jointly evaluates region count accuracy and localization precision. Zero-shot evaluation reveals that partial inpainting at word granularity remains unsolved by existing deepfake detectors: utterance-level classifiers trained on fully synthesized speech assign near zero fake probability to MIST utterances where only 2-7% of content is manipulated. ISA consistently outperforms non-iterative baselines in this challenging setting, and the dataset, code, and evaluation toolkit are publicly released.

Hai Nguyen, Tadashi Kozuno, Cristian C. Beltran-Hernandez et al.

This study tackles the representative yet challenging contact-rich peg-in-hole task of robotic assembly, using a soft wrist that can operate more safely and tolerate lower-frequency control signals than a rigid one. Previous studies often use a fully observable formulation, requiring external setups or estimators for the peg-to-hole pose. In contrast, we use a partially observable formulation and deep reinforcement learning from demonstrations to learn a memory-based agent that acts purely on haptic and proprioceptive signals. Moreover, previous works do not incorporate potential domain symmetry and thus must search for solutions in a bigger space. Instead, we propose to leverage the symmetry for sample efficiency by augmenting the training data and constructing auxiliary losses to force the agent to adhere to the symmetry. Results in simulation with five different symmetric peg shapes show that our proposed agent can be comparable to or even outperform a state-based agent. In particular, the sample efficiency also allows us to learn directly on the real robot within 3 hours.

Khai Nguyen, Hai Nguyen, Tuan Pham et al.

We introduce sliced optimal transport dataset distance (s-OTDD), a model-agnostic, embedding-agnostic approach for dataset comparison that requires no training, is robust to variations in the number of classes, and can handle disjoint label sets. The core innovation is Moment Transform Projection (MTP), which maps a label, represented as a distribution over features, to a real number. Using MTP, we derive a data point projection that transforms datasets into one-dimensional distributions. The s-OTDD is defined as the expected Wasserstein distance between the projected distributions, with respect to random projection parameters. Leveraging the closed form solution of one-dimensional optimal transport, s-OTDD achieves (near-)linear computational complexity in the number of data points and feature dimensions and is independent of the number of classes. With its geometrically meaningful projection, s-OTDD strongly correlates with the optimal transport dataset distance while being more efficient than existing dataset discrepancy measures. Moreover, it correlates well with the performance gap in transfer learning and classification accuracy in data augmentation.

Khai Nguyen, Hai Nguyen, Nhat Ho

We address the problem of efficiently computing Wasserstein distances for multiple pairs of distributions drawn from a meta-distribution. To this end, we propose a fast estimation method based on regressing Wasserstein distance on sliced Wasserstein (SW) distances. Specifically, we leverage both standard SW distances, which provide lower bounds, and lifted SW distances, which provide upper bounds, as predictors of the true Wasserstein distance. To ensure parsimony, we introduce two linear models: an unconstrained model with a closed-form least-squares solution, and a constrained model that uses only half as many parameters. We show that accurate models can be learned from a small number of distribution pairs. Once estimated, the model can predict the Wasserstein distance for any pair of distributions via a linear combination of SW distances, making it highly efficient. Empirically, we validate our approach on diverse tasks, including Gaussian mixtures, point-cloud classification, and Wasserstein-space visualizations for 3D point clouds. Across various datasets such as MNIST point clouds, ShapeNetV2, MERFISH Cell Niches, and scRNA-seq, our method consistently provides a better approximation of Wasserstein distance than the state-of-the-art Wasserstein embedding model, Wasserstein Wormhole, particularly in low-data regimes. Finally, we demonstrate that our estimator can also accelerate Wormhole training, yielding \textit{RG-Wormhole}.

Tung Vu, Hai Nguyen, Cong Tran

Face replacement technology enables significant advancements in entertainment, education, and communication applications, including dubbing, virtual avatars, and cross-cultural content adaptation. Our LiveNeRF framework addresses critical limitations of existing methods by achieving real-time performance (33 FPS) with superior visual quality, enabling practical deployment in live streaming, video conferencing, and interactive media. The technology particularly benefits content creators, educators, and individuals with speech impairments through accessible avatar communication. While acknowledging potential misuse in unauthorized deepfake creation, we advocate for responsible deployment with user consent verification and integration with detection systems to ensure positive societal impact while minimizing risks.

Khai Nguyen, Hai Nguyen, Nhat Ho

The sliced Wasserstein barycenter (SWB) is a widely acknowledged method for efficiently generalizing the averaging operation within probability measure spaces. However, achieving marginal fairness SWB, ensuring approximately equal distances from the barycenter to marginals, remains unexplored. The uniform weighted SWB is not necessarily the optimal choice to obtain the desired marginal fairness barycenter due to the heterogeneous structure of marginals and the non-optimality of the optimization. As the first attempt to tackle the problem, we define the marginal fairness sliced Wasserstein barycenter (MFSWB) as a constrained SWB problem. Due to the computational disadvantages of the formal definition, we propose two hyperparameter-free and computationally tractable surrogate MFSWB problems that implicitly minimize the distances to marginals and encourage marginal fairness at the same time. To further improve the efficiency, we perform slicing distribution selection and obtain the third surrogate definition by introducing a new slicing distribution that focuses more on marginally unfair projecting directions. We discuss the relationship of the three proposed problems and their relationship to sliced multi-marginal Wasserstein distance. Finally, we conduct experiments on finding 3D point-clouds averaging, color harmonization, and training of sliced Wasserstein autoencoder with class-fairness representation to show the favorable performance of the proposed surrogate MFSWB problems.

Sammie Katt, Hai Nguyen, Frans A. Oliehoek et al.

While reinforcement learning (RL) has made great advances in scalability, exploration and partial observability are still active research topics. In contrast, Bayesian RL (BRL) provides a principled answer to both state estimation and the exploration-exploitation trade-off, but struggles to scale. To tackle this challenge, BRL frameworks with various prior assumptions have been proposed, with varied success. This work presents a representation-agnostic formulation of BRL under partially observability, unifying the previous models under one theoretical umbrella. To demonstrate its practical significance we also propose a novel derivation, Bayes-Adaptive Deep Dropout rl (BADDr), based on dropout networks. Under this parameterization, in contrast to previous work, the belief over the state and dynamics is a more scalable inference problem. We choose actions through Monte-Carlo tree search and empirically show that our method is competitive with state-of-the-art BRL methods on small domains while being able to solve much larger ones.

Long H. Nguyen, Nhat Truong Pham, Van Huong Do et al.

SARS-CoV-2 is colloquially known as COVID-19 that had an initial outbreak in December 2019. The deadly virus has spread across the world, taking part in the global pandemic disease since March 2020. In addition, a recent variant of SARS-CoV-2 named Delta is intractably contagious and responsible for more than four million deaths over the world. Therefore, it is vital to possess a self-testing service of SARS-CoV-2 at home. In this study, we introduce Fruit-CoV, a two-stage vision framework, which is capable of detecting SARS-CoV-2 infections through recorded cough sounds. Specifically, we convert sounds into Log-Mel Spectrograms and use the EfficientNet-V2 network to extract its visual features in the first stage. In the second stage, we use 14 convolutional layers extracted from the large-scale Pretrained Audio Neural Networks for audio pattern recognition (PANNs) and the Wavegram-Log-Mel-CNN to aggregate feature representations of the Log-Mel Spectrograms. Finally, we use the combined features to train a binary classifier. In this study, we use a dataset provided by the AICovidVN 115M Challenge, which includes a total of 7371 recorded cough sounds collected throughout Vietnam, India, and Switzerland. Experimental results show that our proposed model achieves an AUC score of 92.8% and ranks the 1st place on the leaderboard of the AICovidVN Challenge. More importantly, our proposed framework can be integrated into a call center or a VoIP system to speed up detecting SARS-CoV-2 infections through online/recorded cough sounds.

Son Thanh Nguyen, Hai Nguyen, Son Tien Bui et al.

This paper presents a novel design of a multi-directional bicycle robot, which targets inspecting general ferromagnetic structures including complex-shaped structures. The locomotion concept is based on arranging two magnetic wheels in a bicycle-like configuration with two independent steering actuators. This configuration allows the robot to possess multi-directional mobility. An additional free joint helps the robot naturally adapt to non-flat and complex surfaces of steel structures. The robot has the biggest advantage to be mechanically simple with high mobility. Besides, the robot is equipped with sensing tools for structure health monitoring. We demonstrate the deployment of our robot to perform steel rust detection on steel bridges. The final inspection results are visualized as 3D models of the bridges together with marked locations of detected rusty areas.

Hai Nguyen, Brett Daley, Xinchao Song et al.

Many important robotics problems are partially observable in the sense that a single visual or force-feedback measurement is insufficient to reconstruct the state. Standard approaches involve learning a policy over beliefs or observation-action histories. However, both of these have drawbacks; it is expensive to track the belief online, and it is hard to learn policies directly over histories. We propose a method for policy learning under partial observability called the Belief-Grounded Network (BGN) in which an auxiliary belief-reconstruction loss incentivizes a neural network to concisely summarize its input history. Since the resulting policy is a function of the history rather than the belief, it can be executed easily at runtime. We compare BGN against several baselines on classic benchmark tasks as well as three novel robotic touch-sensing tasks. BGN outperforms all other tested methods and its learned policies work well when transferred onto a physical robot.

Hoang-Dung Bui, Hai Nguyen, Hung Manh La et al.

Robot manipulation and grasping mechanisms have received considerable attention in the recent past, leading to the development of wide range of industrial applications. This paper proposes the development of an autonomous robotic grasping system for object sorting application. RGB-D data is used by the robot for performing object detection, pose estimation, trajectory generation, and object sorting tasks. The proposed approach can also handle grasping certain objects chosen by users. Trained convolutional neural networks are used to perform object detection and determine the corresponding point cloud cluster of the object to be grasped. From the selected point cloud data, a grasp generator algorithm outputs potential grasps. A grasp filter then scores these potential grasps, and the highest-scored grasp is chosen to execute on a real robot. A motion planner generates collision-free trajectories to execute the chosen grasp. The experiments on AUBO robotic manipulator show the potentials of the proposed approach in the context of autonomous object sorting with robust and fast sorting performance.

Ngoc Duy Nguyen, Thanh Thi Nguyen, Hai Nguyen et al.

The integration of deep learning to reinforcement learning (RL) has enabled RL to perform efficiently in high-dimensional environments. Deep RL methods have been applied to solve many complex real-world problems in recent years. However, development of a deep RL-based system is challenging because of various issues such as the selection of a suitable deep RL algorithm, its network configuration, training time, training methods, and so on. This paper proposes a comprehensive software framework that not only plays a vital role in designing a connect-the-dots deep RL architecture but also provides a guideline to develop a realistic RL application in a short time span. We have designed and developed a deep RL-based software framework that strictly ensures flexibility, robustness, and scalability. By inheriting the proposed architecture, software managers can foresee any challenges when designing a deep RL-based system. As a result, they can expedite the design process and actively control every stage of software development, which is especially critical in agile development environments. To enforce generalization, the proposed architecture does not depend on a specific RL algorithm, a network configuration, the number of agents, or the type of agents. Using our framework, software developers can develop and integrate new RL algorithms or new types of agents, and can flexibly change network configuration or the number of agents.

Adarsh Sehgal, Hung Manh La, Sushil J. Louis et al.

Reinforcement learning (RL) enables agents to take decision based on a reward function. However, in the process of learning, the choice of values for learning algorithm parameters can significantly impact the overall learning process. In this paper, we use a genetic algorithm (GA) to find the values of parameters used in Deep Deterministic Policy Gradient (DDPG) combined with Hindsight Experience Replay (HER), to help speed up the learning agent. We used this method on fetch-reach, slide, push, pick and place, and door opening in robotic manipulation tasks. Our experimental evaluation shows that our method leads to better performance, faster than the original algorithm.

Hai Nguyen, Hung Manh La, Matthew Deans

Supervised learning, more specifically Convolutional Neural Networks (CNN), has surpassed human ability in some visual recognition tasks such as detection of traffic signs, faces and handwritten numbers. On the other hand, even state-of-the-art reinforcement learning (RL) methods have difficulties in environments with sparse and binary rewards. They requires manually shaping reward functions, which might be challenging to come up with. These tasks, however, are trivial to human. One of the reasons that human are better learners in these tasks is that we are embedded with much prior knowledge of the world. These knowledge might be either embedded in our genes or learned from imitation - a type of supervised learning. For that reason, the best way to narrow the gap between machine and human learning ability should be to mimic how we learn so well in various tasks by a combination of RL and supervised learning. Our method, which integrates Deep Deterministic Policy Gradients and Hindsight Experience Replay (RL method specifically dealing with sparse rewards) with an experience ranking CNN, provides a significant speedup over the learning curve on simulated robotics tasks. Experience ranking allows high-reward transitions to be replayed more frequently, and therefore help learn more efficiently. Our proposed approach can also speed up learning in any other tasks that provide additional information for experience ranking.

Hai Nguyen, Shin-ichi Maeda, Kenta Oono

With the rapid increase of compound databases available in medicinal and material science, there is a growing need for learning representations of molecules in a semi-supervised manner. In this paper, we propose an unsupervised hierarchical feature extraction algorithm for molecules (or more generally, graph-structured objects with fixed number of types of nodes and edges), which is applicable to both unsupervised and semi-supervised tasks. Our method extends recently proposed Paragraph Vector algorithm and incorporates neural message passing to obtain hierarchical representations of subgraphs. We applied our method to an unsupervised task and demonstrated that it outperforms existing proposed methods in several benchmark datasets. We also experimentally showed that semi-supervised tasks enhanced predictive performance compared with supervised ones with labeled molecules only.