Domain randomization has emerged as a fundamental technique in reinforcement learning (RL) to facilitate the transfer of policies from simulation to real-world robotic applications. Many existing domain randomization approaches have been proposed to improve robustness and sim2real transfer. These approaches rely on wide randomization ranges to compensate for the unknown actual system parameters, leading to robust but inefficient real-world policies. In addition, the policies pretrained in the domain-randomized simulation are fixed after deployment due to the inherent instability of the optimization processes based on RL and the necessity of sampling exploitative but potentially unsafe actions on the real system. This limits the adaptability of the deployed policy to the inevitably changing system parameters or environment dynamics over time. We leverage safe RL and continual learning under domain-randomized simulation to address these limitations and enable safe deployment-time policy adaptation in real-world robot control. The experiments show that our method enables the policy to adapt and fit to the current domain distribution and environment dynamics of the real system while minimizing safety risks and avoiding issues like catastrophic forgetting of the general policy found in randomized simulation during the pretraining phase. Videos and supplementary material are available at https://safe-cda.github.io/.

Water quality data can supply a substantial decision support for water resources utilization and pollution prevention. However, there are numerous missing values in water quality data due to inescapable factors like sensor failure, thereby leading to biased result for hydrological analysis and failing to support environmental governance decision accurately. A Latent Factorization of Tensors (LFT) with Stochastic Gradient Descent (SGD) proves to be an efficient imputation method. However, a standard SGD-based LFT model commonly surfers from the slow convergence that impairs its efficiency. To tackle this issue, this paper proposes a Fast Latent Factorization of Tensors (FLFT) model. It constructs an adjusted instance error into SGD via leveraging a nonlinear PID controller to incorporates the past, current and future information of prediction error for improving convergence rate. Comparing with state-of-art models in real world datasets, the results of experiment indicate that the FLFT model achieves a better convergence rate and higher accuracy.

This paper tackles decentralized continuous task allocation in heterogeneous multi-agent systems. We present a novel framework HIPPO-MAT that integrates graph neural networks (GNN) employing a GraphSAGE architecture to compute independent embeddings on each agent with an Independent Proximal Policy Optimization (IPPO) approach for multi-agent deep reinforcement learning. In our system, unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) share aggregated observation data via communication channels while independently processing these inputs to generate enriched state embeddings. This design enables dynamic, cost-optimal, conflict-aware task allocation in a 3D grid environment without the need for centralized coordination. A modified A* path planner is incorporated for efficient routing and collision avoidance. Simulation experiments demonstrate scalability with up to 30 agents and preliminary real-world validation on JetBot ROS AI Robots, each running its model on a Jetson Nano and communicating through an ESP-NOW protocol using ESP32-S3, which confirms the practical viability of the approach that incorporates simultaneous localization and mapping (SLAM). Experimental results revealed that our method achieves a high 92.5% conflict-free success rate, with only a 16.49% performance gap compared to the centralized Hungarian method, while outperforming the heuristic decentralized baseline based on greedy approach. Additionally, the framework exhibits scalability with up to 30 agents with allocation processing of 0.32 simulation step time and robustness in responding to dynamically generated tasks.

This work investigates how explicit human feedback can enhance CB performance. Building on successful integrations In recent years, preference-based human feedback of human guidance in reinforcement learning (Christiano mechanisms have become essential for enhancing et al., 2017; MacGlashan et al., 2017) and conversational model performance across diverse applications, AI (Achiam et al., 2023), we distinguish two primary feedback including conversational AI systems such as Chat-paradigms: (1) action-based feedback, where experts GPT. However, existing approaches often neglect directly prescribe optimal actions for specific contexts (Osa critical aspects, such as model uncertainty and et al., 2018; Li et al., 2023), and (2) preference-based feedback, the variability in feedback quality. To address where humans compare pairs of learner-generated actions these challenges, we introduce an entropy-based to express relative preferences (Christiano et al., 2017; human feedback framework for contextual bandits, Saha et al., 2023). While action-based methods require precise which dynamically balances exploration and expert knowledge, we focus on preference feedback for exploitation by soliciting expert feedback only its practical advantages in scalable data collection, notably when model entropy exceeds a predefined threshold.

This paper addresses the challenge of decentralized task allocation within heterogeneous multi-agent systems operating under communication constraints. We introduce a novel framework that integrates graph neural networks (GNNs) with a centralized training and decentralized execution (CTDE) paradigm, further enhanced by a tailored Proximal Policy Optimization (PPO) algorithm for multi-agent deep reinforcement learning (MARL). Our approach enables unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) to dynamically allocate tasks efficiently without necessitating central coordination in a 3D grid environment. The framework minimizes total travel time while simultaneously avoiding conflicts in task assignments. For the cost calculation and routing, we employ reservation-based A* and R* path planners. Experimental results revealed that our method achieves a high 92.5% conflict-free success rate, with only a 7.49% performance gap compared to the centralized Hungarian method, while outperforming the heuristic decentralized baseline based on greedy approach. Additionally, the framework exhibits scalability with up to 20 agents with allocation processing of 2.8 s and robustness in responding to dynamically generated tasks, underscoring its potential for real-world applications in complex multi-agent scenarios.

Group Re-identification (G-ReID) faces greater complexity than individual Re-identification (ReID) due to challenges like mutual occlusion, dynamic member interactions, and evolving group structures. Prior graph-based approaches have aimed to capture these dynamics by modeling the group as a single topological structure. However, these methods struggle to generalize across diverse group compositions, as they fail to fully represent the multifaceted relationships within the group. In this study, we introduce a Hierarchical Multi-Graphs Learning (HMGL) framework to address these challenges. Our approach models the group as a collection of multi-relational graphs, leveraging both explicit features (such as occlusion, appearance, and foreground information) and implicit dependencies between members. This hierarchical representation, encoded via a Multi-Graphs Neural Network (MGNN), allows us to resolve ambiguities in member relationships, particularly in complex, densely populated scenes. To further enhance matching accuracy, we propose a Multi-Scale Matching (MSM) algorithm, which mitigates issues of member information ambiguity and sensitivity to hard samples, improving robustness in challenging scenarios. Our method achieves state-of-the-art performance on two standard benchmarks, CSG and RoadGroup, with Rank-1/mAP scores of 95.3%/94.4% and 93.9%/95.4%, respectively. These results mark notable improvements of 1.7% and 2.5% in Rank-1 accuracy over existing approaches.

In the graph-based semi-supervised learning, the Green-function method is a classical method that works by computing the Green's function in the graph space. However, when applied to large graphs, especially those sparse ones, this method performs unstably and unsatisfactorily. We make a detailed analysis on it and propose a novel method from the perspective of optimization. On fully connected graphs, the method is equivalent to the Green-function method and can be seen as another interpretation with physical meanings, while on non-fully connected graphs, it helps to explain why the Green-function method causes a mess on large sparse graphs. To solve this dilemma, we propose a workable approach to improve our proposed method. Unlike the original method, our improved method can also apply two accelerating techniques, Gaussian Elimination, and Anchored Graphs to become more efficient on large graphs. Finally, the extensive experiments prove our conclusions and the efficiency, accuracy, and stability of our improved Green's function method.

Thompson sampling is one of the most popular learning algorithms for online sequential decision-making problems and has rich real-world applications. However, current Thompson sampling algorithms are limited by the assumption that the rewards received are uncorrupted, which may not be true in real-world applications where adversarial reward poisoning exists. To make Thompson sampling more reliable, we want to make it robust against adversarial reward poisoning. The main challenge is that one can no longer compute the actual posteriors for the true reward, as the agent can only observe the rewards after corruption. In this work, we solve this problem by computing pseudo-posteriors that are less likely to be manipulated by the attack. We propose robust algorithms based on Thompson sampling for the popular stochastic and contextual linear bandit settings in both cases where the agent is aware or unaware of the budget of the attacker. We theoretically show that our algorithms guarantee near-optimal regret under any attack strategy.

Multilevel optimization has gained renewed interest in machine learning due to its promise in applications such as hyperparameter tuning and continual learning. However, existing methods struggle with the inherent difficulty of efficiently handling the nested structure. This paper introduces a novel gradient-based approach for multilevel optimization that overcomes these limitations by leveraging a hierarchically structured decomposition of the full gradient and employing advanced propagation techniques. Extending to n-level scenarios, our method significantly reduces computational complexity while improving both solution accuracy and convergence speed. We demonstrate the effectiveness of our approach through numerical experiments, comparing it with existing methods across several benchmarks. The results show a notable improvement in solution accuracy. To the best of our knowledge, this is one of the first algorithms to provide a general version of implicit differentiation with both theoretical guarantees and superior empirical performance.

Stock trend forecasting, a challenging problem in the financial domain, involves ex-tensive data and related indicators. Relying solely on empirical analysis often yields unsustainable and ineffective results. Machine learning researchers have demonstrated that the application of random forest algorithm can enhance predictions in this context, playing a crucial auxiliary role in forecasting stock trends. This study introduces a new approach to stock market prediction by integrating sentiment analysis using FinGPT generative AI model with the traditional Random Forest model. The proposed technique aims to optimize the accuracy of stock price forecasts by leveraging the nuanced understanding of financial sentiments provided by FinGPT. We present a new methodology called "Sentiment-Augmented Random Forest" (SARF), which in-corporates sentiment features into the Random Forest framework. Our experiments demonstrate that SARF outperforms conventional Random Forest and LSTM models with an average accuracy improvement of 9.23% and lower prediction errors in pre-dicting stock market movements.