-- The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance, frequently without considering risk or safety. In contrast, safe reinforcement learning seeks to reduce or avoid unsafe states. This letter introduces a risk-averse temporal difference algorithm that uses optimal transport theory to direct the agent toward predictable behavior . By incorporating a risk indicator, the agent learns to favor actions with predictable consequences. We evaluate the proposed algorithm in several case studies and show its effectiveness in the presence of uncertainty. The results demonstrate that our method reduces the frequency of visits to risky states while preserving performance. I. INTRODUCTION Reinforcement learning (RL) algorithms focus on maximizing performance, primarily through long-term reward optimization. However, this objective alone does not always prevent negative or high-risk outcomes.

Thus, the observed data can be summarized into a sequence of "observation-action-reward" triplets ( O t, A t, R t) t 0. It is worth noting that the observation O t at each time step is not equivalent to the environment's state S t. Indeed, the state can be viewed as a special observation with the Markov property, and we will elaborate on the difference between the two later. Policies: The goal of RL is to learn an optimal policy π based on the observation-action-reward triplets to maximize the agent's cumulative reward. Mathematically, a policy is defined as a conditional probability distribution function mapping the agent's observed data history to the action space. It specifies the probability of the agent taking different actions at each time step. Below, we introduce three types of policies (see Figure 1(b) for a visualization of their relationships): (1) History-dependent policy: This is the most general form of policy. At each time t, we define H t as the set containing the current observation O t and all prior historical information (O i, A i, R i) i

Reinforcement learning plays a crucial role in vehicle control by guiding agents to learn optimal control strategies through designing or learning appropriate reward signals. However, in vehicle control applications, rewards typically need to be manually designed while considering multiple implicit factors, which easily introduces human biases. Although imitation learning methods does not rely on explicit reward signals, they necessitate high-quality expert actions, which are often challenging to acquire. To address these issues, we propose a reward-free reinforcement learning framework (RFRLF). This framework directly learns the target states to optimize agent behavior through a target state prediction network (TSPN) and a reward-free state-guided policy network (RFSGPN), avoiding the dependence on manually designed reward signals. Specifically, the policy network is learned via minimizing the differences between the predicted state and the expert state. Experimental results demonstrate the effectiveness of the proposed RFRLF in controlling vehicle driving, showing its advantages in improving learning efficiency and adapting to reward-free environments.

Modern deep reinforcement learning (DRL) methods have made significant advances in handling continuous action spaces. However, real-world control systems--especially those requiring precise and reliable performance--often demand formal stability, and existing DRL approaches typically lack explicit mechanisms to ensure or analyze stability. To address this limitation, we propose SALSA-RL (Stability Analysis in the Latent Space of Actions), a novel RL framework that models control actions as dynamic, time-dependent variables evolving within a latent space. By employing a pre-trained encoder-decoder and a state-dependent linear system, our approach enables both stability analysis and interpretability. We demonstrated that SALSA-RL can be deployed in a non-invasive manner for assessing the local stability of actions from pretrained RL agents without compromising on performance across diverse benchmark environments. By enabling a more interpretable analysis of action generation, SALSA-RL provides a powerful tool for advancing the design, analysis, and theoretical understanding of RL systems.

Efficient task allocation among multiple robots is crucial for optimizing productivity in modern warehouses, particularly in response to the increasing demands of online order fulfillment. This paper addresses the real-time multi-robot task allocation (MRTA) problem in dynamic warehouse environments, where tasks emerge with specified start and end locations. The objective is to minimize both the total travel distance of robots and delays in task completion, while also considering practical constraints such as battery management and collision avoidance. We introduce MRTAgent, a dual-agent Reinforcement Learning (RL) framework inspired by self-play, designed to optimize task assignments and robot selection to ensure timely task execution. For safe navigation, a modified linear quadratic controller (LQR) approach is employed. To the best of our knowledge, MRTAgent is the first framework to address all critical aspects of practical MRTA problems while supporting continuous robot movements.

Given the complexity of multi-tenant cloud environments and the need for real-time threat mitigation, Security Operations Centers (SOCs) must integrate AI-driven adaptive defenses against Advanced Persistent Threats (APTs). However, SOC analysts struggle with countering adaptive adversarial tactics, necessitating intelligent decision-support frameworks. To enhance human-AI collaboration in SOCs, we propose a Cognitive Hierarchy Theory-driven Deep Q-Network (CHT-DQN) framework that models SOC analysts' decision-making against AI-driven APT bots. The SOC analyst (defender) operates at cognitive level-1, anticipating attacker strategies, while the APT bot (attacker) follows a level-0 exploitative policy. By incorporating CHT into DQN, our framework enhances SOC defense strategies via Attack Graph (AG)-based reinforcement learning. Simulation experiments across varying AG complexities show that CHT-DQN achieves higher data protection and lower action discrepancies compared to standard DQN. A theoretical lower bound analysis further validates its superior Q-value performance. A human-in-the-loop (HITL) evaluation on Amazon Mechanical Turk (MTurk) reveals that SOC analysts using CHT-DQN-driven transition probabilities align better with adaptive attackers, improving data protection. Additionally, human decision patterns exhibit risk aversion after failure and risk-seeking behavior after success, aligning with Prospect Theory. These findings underscore the potential of integrating cognitive modeling into deep reinforcement learning to enhance SOC operations and develop real-time adaptive cloud security mechanisms.

Soft robots, made from compliant materials, exhibit complex dynamics due to their flexibility and high degrees of freedom. Controlling soft robots presents significant challenges, particularly underactuation, where the number of inputs is fewer than the degrees of freedom. This research aims to develop a digital twin for multi-fingered soft grippers to advance the development of underactuation algorithms. The digital twin is designed to capture key effects observed in soft robots, such as nonlinearity, hysteresis, uncertainty, and time-varying phenomena, ensuring it closely replicates the behavior of a real-world soft gripper. Uncertainty is simulated using the Monte Carlo method. With the digital twin, a Q-learning algorithm is preliminarily applied to identify the optimal motion speed that minimizes uncertainty caused by the soft robots. Underactuated motions are successfully simulated within this environment. This digital twin paves the way for advanced machine learning algorithm training.

Proximal policy optimization (PPO) is one of the most popular state-of-the-art on-policy algorithms that has become a standard baseline in modern reinforcement learning with applications in numerous fields. Though it delivers stable performance with theoretical policy improvement guarantees, high variance, and high sample complexity still remain critical challenges in on-policy algorithms. To alleviate these issues, we propose Hybrid-Policy Proximal Policy Optimization (HP3O), which utilizes a trajectory replay buffer to make efficient use of trajectories generated by recent policies. Particularly, the buffer applies the "first in, first out" (FIFO) strategy so as to keep only the recent trajectories to attenuate the data distribution drift. A batch consisting of the trajectory with the best return and other randomly sampled ones from the buffer is used for updating the policy networks. The strategy helps the agent to improve its capability on top of the most recent best performance and in turn reduce variance empirically. We theoretically construct the policy improvement guarantees for the proposed algorithm. HP3O is validated and compared against several baseline algorithms using multiple continuous control environments. Our code is available here.

Reinforcement learning (RL) algorithms have been successfully applied to control tasks associated with unmanned aerial vehicles and robotics. In recent years, safe RL has been proposed to allow the safe execution of RL algorithms in industrial and mission-critical systems that operate in closed loops. However, if the system operating conditions change, such as when an unknown fault occurs in the system, typical safe RL algorithms are unable to adapt while retaining past knowledge. Continual reinforcement learning algorithms have been proposed to address this issue. However, the impact of continual adaptation on the system's safety is an understudied problem. In this paper, we study the intersection of safe and continual RL. First, we empirically demonstrate that a popular continual RL algorithm, online elastic weight consolidation, is unable to satisfy safety constraints in non-linear systems subject to varying operating conditions. Specifically, we study the MuJoCo HalfCheetah and Ant environments with velocity constraints and sudden joint loss non-stationarity. Then, we show that an agent trained using constrained policy optimization, a safe RL algorithm, experiences catastrophic forgetting in continual learning settings. With this in mind, we explore a simple reward-shaping method to ensure that elastic weight consolidation prioritizes remembering both safety and task performance for safety-constrained, non-linear, and non-stationary dynamical systems.

A major challenge for reinforcement learning is automatically generating curricula to reduce training time or improve performance in some target task. We introduce SEBNs (Skill-Environment Bayesian Networks) which model a probabilistic relationship between a set of skills, a set of goals that relate to the reward structure, and a set of environment features to predict policy performance on (possibly unseen) tasks. We develop an algorithm that uses the inferred estimates of agent success from SEBN to weigh the possible next tasks by expected improvement. We evaluate the benefit of the resulting curriculum on three environments: a discrete gridworld, continuous control, and simulated robotics. The results show that curricula constructed using SEBN frequently outperform other baselines.