The performance of offline reinforcement learning (RL) suffers from the limited size and quality of static datasets. Model-based offline RL addresses this issue by generating synthetic samples through a dynamics model to enhance overall performance. To evaluate the reliability of the generated samples, uncertainty estimation methods are often employed. However, model ensemble, the most commonly used uncertainty estimation method, is not always the best choice. In this paper, we propose a \textbf{S}earch-based \textbf{U}ncertainty estimation method for \textbf{M}odel-based \textbf{O}ffline RL (SUMO) as an alternative. SUMO characterizes the uncertainty of synthetic samples by measuring their cross entropy against the in-distribution dataset samples, and uses an efficient search-based method for implementation. In this way, SUMO can achieve trustworthy uncertainty estimation. We integrate SUMO into several model-based offline RL algorithms including MOPO and Adapted MOReL (AMOReL), and provide theoretical analysis for them. Extensive experimental results on D4RL datasets demonstrate that SUMO can provide more accurate uncertainty estimation and boost the performance of base algorithms. These indicate that SUMO could be a better uncertainty estimator for model-based offline RL when used in either reward penalty or trajectory truncation. Our code is available and will be open-source for further research and development.

In comparison to common quadrotors, the shape change of morphing quadrotors endows it with a more better flight performance but also results in more complex flight dynamics. Generally, it is extremely difficult or even impossible for morphing quadrotors to establish an accurate mathematical model describing their complex flight dynamics. To figure out the issue of flight control design for morphing quadrotors, this paper resorts to a combination of model-free control techniques (e.g., deep reinforcement learning, DRL) and convex combination (CC) technique, and proposes a convex-combined-DRL (cc-DRL) flight control algorithm for position and attitude of a class of morphing quadrotors, where the shape change is realized by the length variation of four arm rods. In the proposed cc-DRL flight control algorithm, proximal policy optimization algorithm that is a model-free DRL algorithm is utilized to off-line train the corresponding optimal flight control laws for some selected representative arm length modes and hereby a cc-DRL flight control scheme is constructed by the convex combination technique. Finally, simulation results are presented to show the effectiveness and merit of the proposed flight control algorithm.

Offline multi-agent reinforcement learning (MARL) is increasingly recognized as crucial for effectively deploying RL algorithms in environments where real-time interaction is impractical, risky, or costly. In the offline setting, learning from a static dataset of past interactions allows for the development of robust and safe policies without the need for live data collection, which can be fraught with challenges. Building on this foundational importance, we present EAQ, Episodes Augmentation guided by Q-total loss, a novel approach for offline MARL framework utilizing diffusion models. EAQ integrates the Q-total function directly into the diffusion model as a guidance to maximize the global returns in an episode, eliminating the need for separate training. Our focus primarily lies on cooperative scenarios, where agents are required to act collectively towards achieving a shared goal-essentially, maximizing global returns. Consequently, we demonstrate that our episodes augmentation in a collaborative manner significantly boosts offline MARL algorithm compared to the original dataset, improving the normalized return by +17.3% and +12.9% for medium and poor behavioral policies in SMAC simulator, respectively.

Centralized training for decentralized execution paradigm emerged as the state-of-the-art approach to epsilon-optimally solving decentralized partially observable Markov decision processes. However, scalability remains a significant issue. This paper presents a novel and more scalable alternative, namely sequential-move centralized training for decentralized execution. This paradigm further pushes the applicability of Bellman's principle of optimality, raising three new properties. First, it allows a central planner to reason upon sufficient sequential-move statistics instead of prior simultaneous-move ones. Next, it proves that epsilon-optimal value functions are piecewise linear and convex in sufficient sequential-move statistics. Finally, it drops the complexity of the backup operators from double exponential to polynomial at the expense of longer planning horizons. Besides, it makes it easy to use single-agent methods, e.g., SARSA algorithm enhanced with these findings applies while still preserving convergence guarantees. Experiments on two- as well as many-agent domains from the literature against epsilon-optimal simultaneous-move solvers confirm the superiority of the novel approach. This paradigm opens the door for efficient planning and reinforcement learning methods for multi-agent systems.

In the domain of combat simulations, the training and deployment of deep reinforcement learning (RL) agents still face substantial challenges due to the dynamic and intricate nature of such environments. Unfortunately, as the complexity of the scenarios and available information increases, the training time required to achieve a certain threshold of performance does not just increase, but often does so exponentially. This relationship underscores the profound impact of complexity in training RL agents. This paper introduces a novel approach that addresses this limitation in training artificial intelligence (AI) agents using RL. Traditional RL methods have been shown to struggle in these high-dimensional, dynamic environments due to real-world computational constraints and the known sample inefficiency challenges of RL. To overcome these limitations, we propose a method of localized observation abstraction using piecewise linear spatial decay. This technique simplifies the state space, reducing computational demands while still preserving essential information, thereby enhancing AI training efficiency in dynamic environments where spatial relationships are often critical. Our analysis reveals that this localized observation approach consistently outperforms the more traditional global observation approach across increasing scenario complexity levels. This paper advances the research on observation abstractions for RL, illustrating how localized observation with piecewise linear spatial decay can provide an effective solution to large state representation challenges in dynamic environments.

Uncertainty quantification in travel time estimation (TTE) aims to estimate the confidence interval for travel time, given the origin (O), destination (D), and departure time (T). Accurately quantifying this uncertainty requires generating the most likely path and assessing travel time uncertainty along the path. This involves two main challenges: 1) Predicting a path that aligns with the ground truth, and 2) modeling the impact of travel time in each segment on overall uncertainty under varying conditions. We propose DutyTTE to address these challenges. For the first challenge, we introduce a deep reinforcement learning method to improve alignment between the predicted path and the ground truth, providing more accurate travel time information from road segments to improve TTE. For the second challenge, we propose a mixture of experts guided uncertainty quantification mechanism to better capture travel time uncertainty for each segment under varying contexts. Additionally, we calibrate our results using Hoeffding's upper-confidence bound to provide statistical guarantees for the estimated confidence intervals. Extensive experiments on two real-world datasets demonstrate the superiority of our proposed method.

Continuous electroencephalography (EEG) signals are widely used in affective brain-computer interface (aBCI) applications. However, not all continuously collected EEG signals are relevant or meaningful to the task at hand (e.g., wondering thoughts). On the other hand, manually labeling the relevant parts is nearly impossible due to varying engagement patterns across different tasks and individuals. Therefore, effectively and efficiently identifying the important parts from continuous EEG recordings is crucial for downstream BCI tasks, as it directly impacts the accuracy and reliability of the results. In this paper, we propose a novel unsupervised deep reinforcement learning framework, called Emotion-Agent, to automatically identify relevant and informative emotional moments from continuous EEG signals. Specifically, Emotion-Agent involves unsupervised deep reinforcement learning combined with a heuristic algorithm. We first use the heuristic algorithm to perform an initial global search and form prototype representations of the EEG signals, which facilitates the efficient exploration of the signal space and identify potential regions of interest. Then, we design distribution-prototype reward functions to estimate the interactions between samples and prototypes, ensuring that the identified parts are both relevant and representative of the underlying emotional states. Emotion-Agent is trained using Proximal Policy Optimization (PPO) to achieve stable and efficient convergence. Our experiments compare the performance with and without Emotion-Agent. The results demonstrate that selecting relevant and informative emotional parts before inputting them into downstream tasks enhances the accuracy and reliability of aBCI applications.

Learning to manipulate dynamic and deformable objects from a single demonstration video holds great promise in terms of scalability. Previous approaches have predominantly focused on either replaying object relationships or actor trajectories. The former often struggles to generalize across diverse tasks, while the latter suffers from data inefficiency. Moreover, both methodologies encounter challenges in capturing invisible physical attributes, such as forces. In this paper, we propose to interpret video demonstrations through Parameterized Symbolic Abstraction Graphs (PSAG), where nodes represent objects and edges denote relationships between objects. We further ground geometric constraints through simulation to estimate non-geometric, visually imperceptible attributes. The augmented PSAG is then applied in real robot experiments. Our approach has been validated across a range of tasks, such as Cutting Avocado, Cutting Vegetable, Pouring Liquid, Rolling Dough, and Slicing Pizza. We demonstrate successful generalization to novel objects with distinct visual and physical properties.

The neutrality thesis holds that technology cannot be laden with values. This long-standing view has faced critiques, but much of the argumentation against neutrality has focused on traditional, non-smart technologies like bridges and razors. In contrast, AI is a smart technology increasingly used in high-stakes domains like healthcare, finance, and policing, where its decisions can cause moral harm. In this paper, we argue that artificial intelligence, particularly artificial agents that autonomously make decisions to pursue their goals, challenge the neutrality thesis. Our central claim is that the computational models underlying artificial agents can integrate representations of moral values such as fairness, honesty and avoiding harm. We provide a conceptual framework discussing the neutrality thesis, values, and AI. Moreover, we examine two approaches to designing computational models of morality, artificial conscience and ethical prompting, and present empirical evidence from text-based game environments that artificial agents with such models exhibit more ethical behavior compared to agents without these models. The findings support that AI can embody moral values, which contradicts the claim that all technologies are necessarily value-neutral.

Autonomous vehicles with a self-evolving ability are expected to cope with unknown scenarios in the real-world environment. Take advantage of trial and error mechanism, reinforcement learning is able to self evolve by learning the optimal policy, and it is particularly well suitable for solving decision-making problems. However, reinforcement learning suffers from safety issues and low learning efficiency, especially in the continuous action space. Therefore, the motivation of this paper is to address the above problem by proposing a hybrid Mechanism-Experience-Learning augmented approach. Specifically, to realize the efficient self-evolution, the driving tendency by analogy with human driving experience is proposed to reduce the search space of the autonomous driving problem, while the constrained optimization problem based on a mechanistic model is designed to ensure safety during the self-evolving process. Experimental results show that the proposed method is capable of generating safe and reasonable actions in various complex scenarios, improving the performance of the autonomous driving system. Compared to conventional reinforcement learning, the safety and efficiency of the proposed algorithm are greatly improved. The training process is collision-free, and the training time is equivalent to less than 10 minutes in the real world.