Dynamic treatment regimes (DTRs) are critical to precision medicine, optimizing long-term outcomes through personalized, real-time decision-making in evolving clinical contexts, but require careful supervision for unsafe treatment risks. Existing efforts rely primarily on clinician-prescribed gold standards despite the absence of a known optimal strategy, and predominantly using structured EHR data without extracting valuable insights from clinical notes, limiting their reliability for treatment recommendations. In this work, we introduce SAFER, a calibrated risk-aware tabular-language recommendation framework for DTR that integrates both structured EHR and clinical notes, enabling them to learn from each other, and addresses inherent label uncertainty by assuming ambiguous optimal treatment solution for deceased patients. Moreover, SAFER employs conformal prediction to provide statistical guarantees, ensuring safe treatment recommendations while filtering out uncertain predictions. Experiments on two publicly available sepsis datasets demonstrate that SAFER outperforms state-of-the-art baselines across multiple recommendation metrics and counterfactual mortality rate, while offering robust formal assurances. These findings underscore SAFER potential as a trustworthy and theoretically grounded solution for high-stakes DTR applications.

We present the first $Q$-learning and actor-critic algorithms for robust average reward Markov Decision Processes (MDPs) with non-asymptotic convergence under contamination, TV distance and Wasserstein distance uncertainty sets. We show that the robust $Q$ Bellman operator is a strict contractive mapping with respect to a carefully constructed semi-norm with constant functions being quotiented out. This property supports a stochastic approximation update, that learns the optimal robust $Q$ function in $\tilde{\cO}(ε^{-2})$ samples. We also show that the same idea can be used for robust $Q$ function estimation, which can be further used for critic estimation. Coupling it with theories in robust policy mirror descent update, we present a natural actor-critic algorithm that attains an $ε$-optimal robust policy in $\tilde{\cO}(ε^{-3})$ samples. These results advance the theory of distributionally robust reinforcement learning in the average reward setting.

Realistic urban traffic simulation is essential for sustainable urban planning and the development of intelligent transportation systems. However, generating high-fidelity, time-varying traffic profiles that accurately reflect real-world conditions, especially in large-scale scenarios, remains a major challenge. Existing methods often suffer from limitations in accuracy, scalability, or raise privacy concerns due to centralized data processing. This work introduces DesRUTGe (Decentralized Realistic Urban Traffic Generator), a novel framework that integrates Deep Reinforcement Learning (DRL) agents with the SUMO simulator to generate realistic 24-hour traffic patterns. A key innovation of DesRUTGe is its use of Decentralized Federated Learning (DFL), wherein each traffic detector and its corresponding urban zone function as an independent learning node. These nodes train local DRL models using minimal historical data and collaboratively refine their performance by exchanging model parameters with selected peers (e.g., geographically adjacent zones), without requiring a central coordinator. Evaluated using real-world data from the city of Barcelona, DesRUTGe outperforms standard SUMO-based tools such as RouteSampler, as well as other centralized learning approaches, by delivering more accurate and privacy-preserving traffic pattern generation.

Multi-agent reinforcement learning (MARL) has achieved strong performance in cooperative adversarial tasks. However, most existing methods typically train agents against fixed opponent strategies and rely on such meta-static difficulty conditions, which limits their adaptability to changing environments and often leads to suboptimal policies. Inspired by the success of curriculum learning (CL) in supervised tasks, we propose a dynamic CL framework for MARL that employs an self-adaptive difficulty adjustment mechanism. This mechanism continuously modulates opponent strength based on real-time agent training performance, allowing agents to progressively learn from easier to more challenging scenarios. However, the dynamic nature of CL introduces instability due to nonstationary environments and sparse global rewards. To address this challenge, we develop a Counterfactual Group Relative Policy Advantage (CGRPA), which is tightly coupled with the curriculum by providing intrinsic credit signals that reflect each agent's impact under evolving task demands. CGRPA constructs a counterfactual advantage function that isolates individual contributions within group behavior, facilitating more reliable policy updates throughout the curriculum. CGRPA evaluates each agent's contribution through constructing counterfactual action advantage function, providing intrinsic rewards that enhance credit assignment and stabilize learning under non-stationary conditions. Extensive experiments demonstrate that our method improves both training stability and final performance, achieving competitive results against state-of-the-art methods. The code is available at https://github.com/NICE-HKU/CL2MARL-SMAC.

We study the problem of sample efficient reinforcement learning, where prior data such as demonstrations are provided for initialization in lieu of a dense reward signal. A natural approach is to incorporate an imitation learning objective, either as regularization during training or to acquire a reference policy. However, imitation learning objectives can ultimately degrade long-term performance, as it does not directly align with reward maximization. In this work, we propose to use prior data solely for guiding exploration via noise added to the policy, sidestepping the need for explicit behavior cloning constraints. The key insight in our framework, Data-Guided Noise (DGN), is that demonstrations are most useful for identifying which actions should be explored, rather than forcing the policy to take certain actions. Our approach achieves up to 2-3x improvement over prior reinforcement learning from offline data methods across seven simulated continuous control tasks.

As the scale and complexity of cloud-based AI systems continue to increase, the detection and adaptive recovery of system faults have become the core challenges to ensure service reliability and continuity. In this paper, we propose an Intelligent Fault Self-Healing Mechanism (IFSHM) that integrates Large Language Model (LLM) and Deep Reinforcement Learning (DRL), aiming to realize a fault recovery framework with semantic understanding and policy optimization capabilities in cloud AI systems. On the basis of the traditional DRL-based control model, the proposed method constructs a two-stage hybrid architecture: (1) an LLM-driven fault semantic interpretation module, which can dynamically extract deep contextual semantics from multi-source logs and system indicators to accurately identify potential fault modes; (2) DRL recovery strategy optimizer, based on reinforcement learning, learns the dynamic matching of fault types and response behaviors in the cloud environment. The innovation of this method lies in the introduction of LLM for environment modeling and action space abstraction, which greatly improves the exploration efficiency and generalization ability of reinforcement learning. At the same time, a memory-guided meta-controller is introduced, combined with reinforcement learning playback and LLM prompt fine-tuning strategy, to achieve continuous adaptation to new failure modes and avoid catastrophic forgetting. Experimental results on the cloud fault injection platform show that compared with the existing DRL and rule methods, the IFSHM framework shortens the system recovery time by 37% with unknown fault scenarios.

Classical policy gradient (PG) methods in reinforcement learning frequently converge to suboptimal local optima, a challenge exacerbated in large or complex environments. This work investigates Policy Gradient with Tree Search (PGTS), an approach that integrates an $m$-step lookahead mechanism to enhance policy optimization. We provide theoretical analysis demonstrating that increasing the tree search depth $m$-monotonically reduces the set of undesirable stationary points and, consequently, improves the worst-case performance of any resulting stationary policy. Critically, our analysis accommodates practical scenarios where policy updates are restricted to states visited by the current policy, rather than requiring updates across the entire state space. Empirical evaluations on diverse MDP structures, including Ladder, Tightrope, and Gridworld environments, illustrate PGTS's ability to exhibit "farsightedness," navigate challenging reward landscapes, escape local traps where standard PG fails, and achieve superior solutions.

Reinforcement Learning (RL) has outperformed other counterparts in sequential decision-making and dynamic environment control. However, FPGA deployment is significantly resource-expensive, as associated with large number of computations in training agents with high-quality images and possess new challenges. In this work, we propose QForce-RL takes benefits of quantization to enhance throughput and reduce energy footprint with light-weight RL architecture, without significant performance degradation. QForce-RL takes advantages from E2HRL to reduce overall RL actions to learn desired policy and QuaRL for quantization based SIMD for hardware acceleration. We have also provided detailed analysis for different RL environments, with emphasis on model size, parameters, and accelerated compute ops. The architecture is scalable for resource-constrained devices and provide parametrized efficient deployment with flexibility in latency, throughput, power, and energy efficiency. The proposed QForce-RL provides performance enhancement up to 2.3x and better FPS - 2.6x compared to SoTA works.

--Using Reinforcement Learning (RL) to learn new robotic tasks from scratch is often inefficient. Leveraging prior knowledge has the potential to significantly enhance learning efficiency, which, however, raises two critical challenges: how to determine the relevancy of existing knowledge and how to adap-tively integrate them into learning a new task. CARoL incorporates context awareness by analyzing state transitions in system dynamics to identify similarities between the new task and prior knowledge. It then utilizes these identified similarities to prioritize and adapt specific knowledge pieces for the new task. Additionally, CARoL has a broad applicability spanning policy-based, value-based, and actor-critic RL algorithms. The simulations include CarRacing and LunarLander environments, where CARoL demonstrates faster convergence and higher rewards when learning policies for new tasks. In real-world experiments, we show that CARoL enables a ground vehicle to quickly and efficiently adapt policies learned in simulation to smoothly traverse real-world off-road terrain. In recent years, Reinforcement Learning (RL) approaches have achieved remarkable success in advanced robotic control and complex task learning in dynamic environments, enabling applications across various domains, such as autonomous navigation [36, 38], manipulation [28, 42], and human-robot interaction [23]. Despite these advancements, RL methods are typically computationally demanding, as they rely on repeated trial-and-error exploration to discover high-reward outcomes. Knowledge fusion [2] and adaptation [24, 35] provide promising approaches to address the inefficiency of RL. They leverage knowledge (such as a learned control policy, approximated value function, etc.) from previously explored tasks to accelerate training on new tasks, eliminating the need to train from scratch for every scenario. For example, consider a vehicle navigating highly complex off-road terrain as shown in Figure 1. Suppose the vehicle has undergone extensive training in several existing environments, it should ideally be capable of adapting to a new type of terrain by utilizing previously learned knowledge.

Markov Decision Processes (MDPs) are the most common model for decision making under uncertainty in the Machine Learning community. An MDP captures non-determinism, probabilistic uncertainty, and an explicit model of action. A Reinforcement Learning (RL) agent learns to act in an MDP by maximizing a utility function. This paper considers the problem of learning a decision policy that maximizes utility subject to satisfying a constraint expressed in deontic logic. In this setup, the utility captures the agent's mission - such as going quickly from A to B. The deontic formula represents (ethical, social, situational) constraints on how the agent might achieve its mission by prohibiting classes of behaviors. We use the logic of Expected Act Utilitarianism, a probabilistic stit logic that can be interpreted over controlled MDPs. We develop a variation on policy improvement, and show that it reaches a constrained local maximum of the mission utility. Given that in stit logic, an agent's duty is derived from value maximization, this can be seen as a way of acting to simultaneously maximize two value functions, one of which is implicit, in a bi-level structure. We illustrate these results with experiments on sample MDPs.