In this work, we provide an extended discussion of a new approach to explainable Reinforcement Learning called Diverse Near-Optimal Alternatives (DNA), first proposed at L4DC 2025. DNA seeks a set of reasonable "options" for trajectory-planning agents, optimizing policies to produce qualitatively diverse trajectories in Euclidean space. In the spirit of explainability, these distinct policies are used to "explain" an agent's options in terms of available trajectory shapes from which a human user may choose. In particular, DNA applies to value function-based policies on Markov decision processes where agents are limited to continuous trajectories. Here, we describe DNA, which uses reward shaping in local, modified Q-learning problems to solve for distinct policies with guaranteed epsilon-optimality. We show that it successfully returns qualitatively different policies that constitute meaningfully different "options" in simulation, including a brief comparison to related approaches in the stochastic optimization field of Quality Diversity. Beyond the explanatory motivation, this work opens new possibilities for exploration and adaptive planning in RL.

-- Adversarial attacks and robustness in Deep Reinforcement Learning (DRL) have been widely studied in various threat models; however, few consider environmental state perturbations, which are natural in embodied scenarios. T o improve the robustness of DRL agents, we formulate the problem of environmental state perturbation, introducing a preliminary non-targeted attack method as a calibration adversary, and then propose a defense framework, named Boosted Adversarial Training (BA T), which first tunes the agents via supervised learning to avoid catastrophic failure and subsequently adversarially trains the agent with reinforcement learning. Extensive experimental results substantiate the vulnerability of mainstream agents under environmental state perturbations and the effectiveness of our proposed attack. The defense results demonstrate that while existing robust reinforcement learning algorithms may not be suitable, our BA T framework can significantly enhance the robustness of agents against environmental state perturbations across various situations. The safety and robustness of Deep Reinforcement Learning (DRL) have been receiving increasing attention and have been studied in various domains, such as perturbation on the observation [1], [2], [3], [4] or the action [5], data poisoning [6], [7], adversarial policies [8], and multi-agent reinforcement learning [9], [10]. However, few works focus on the environmental robustness of the agent, which may be crucial for further applying DRL to robotic applications. In application, robots may be deployed in various environments that are different from the training one, with either unconscious or even malicious perturbations, such as placing or moving task-irrelevant objects. The limitations ensure the alignment between the problem we studied and robotic application scenarios in reality, where the perturbation is practical and corresponding attacks are realizable.

Real-time cascade mitigation requires fast, complex operational decisions under uncertainty. In this work, we extend the influence graph into a Markov decision process model (MDP) for real-time mitigation of cascading outages in power transmission systems, accounting for uncertainties in generation, load, and initial contingencies. The MDP includes a do-nothing action to allow for conservative decision-making and is solved using reinforcement learning. We present a policy gradient learning algorithm initialized with a policy corresponding to the unmitigated case and designed to handle invalid actions. The proposed learning method converges faster than the conventional algorithm. Through careful reward design, we learn a policy that takes conservative actions without deteriorating system conditions. The model is validated on the IEEE 14-bus and IEEE 118-bus systems. The results show that proactive line disconnections can effectively reduce cascading risk, and certain lines consistently emerge as critical in mitigating cascade propagation.

Soft real-time applications are becoming increasingly complex, posing significant challenges for scheduling offloaded tasks in edge computing environments while meeting task timing constraints. Moreover, the exponential growth of the search space, presence of multiple objectives and parameters, and highly dynamic nature of edge computing environments further exacerbate the complexity of task scheduling. As a result, schedulers based on heuristic and metaheuristic algorithms frequently encounter difficulties in generating optimal or near-optimal task schedules due to their constrained ability to adapt to the dynamic conditions and complex environmental characteristics of edge computing. Accordingly, reinforcement learning algorithms have been incorporated into schedulers to address the complexity and dynamic conditions inherent in task scheduling in edge computing. However, a significant limitation of reinforcement learning algorithms is the prolonged learning time required to adapt to new environments and to address medium- and large-scale problems. This challenge arises from the extensive global action space and frequent random exploration of irrelevant actions. Therefore, this study proposes Agile Reinforcement learning (aRL), in which the RL-agent performs informed exploration and executes only relevant actions. Consequently, the predictability of the RL-agent is enhanced, leading to rapid adaptation and convergence, which positions aRL as a suitable candidate for scheduling the tasks of soft real-time applications in edge computing. The experiments demonstrate that the combination of informed exploration and action-masking methods enables aRL to achieve a higher hit-ratio and converge faster than the baseline approaches.

Recent advances of Reinforcement Learning (RL) have highlighted its potential in complex reasoning tasks, yet effective training often relies on external supervision, which limits the broader applicability. In this work, we propose a novel self-rewarding reinforcement learning framework to enhance Large Language Model (LLM) reasoning by leveraging the consistency of intermediate reasoning states across different reasoning trajectories. Our key insight is that correct responses often exhibit consistent trajectory patterns in terms of model likelihood: their intermediate reasoning states tend to converge toward their own final answers (high consistency) with minimal deviation toward other candidates (low volatility). Inspired by this observation, we introduce CoVo, an intrinsic reward mechanism that integrates Consistency and Volatility via a robust vector-space aggregation strategy, complemented by a curiosity bonus to promote diverse exploration. CoVo enables LLMs to perform RL in a self-rewarding manner, offering a scalable pathway for learning to reason without external supervision. Extensive experiments on diverse reasoning benchmarks show that CoVo achieves performance comparable to or even surpassing supervised RL. Our code is available at https://github.com/sastpg/CoVo.

Stationary Distribution Correction Estimation (DICE) addresses the mismatch between the stationary distribution induced by a policy and the target distribution required for reliable off-policy evaluation (OPE) and policy optimization. DICE-based offline constrained RL particularly benefits from the flexibility of DICE, as it simultaneously maximizes return while estimating costs in offline settings. However, we have observed that recent approaches designed to enhance the offline RL performance of the DICE framework inadvertently undermine its ability to perform OPE, making them unsuitable for constrained RL scenarios. In this paper, we identify the root cause of this limitation: their reliance on a semi-gradient optimization, which solves a fundamentally different optimization problem and results in failures in cost estimation. Building on these insights, we propose a novel method to enable OPE and constrained RL through semi-gradient DICE. Our method ensures accurate cost estimation and achieves state-of-the-art performance on the offline constrained RL benchmark, DSRL.

Two-stage Colonel Blotto game represents a typical adversarial resource allocation problem, in which two opposing agents sequentially allocate resources in a network topology across two phases: an initial resource deployment followed by multiple rounds of dynamic reallocation adjustments. The sequential dependency between game stages and the complex constraints imposed by the graph topology make it difficult for traditional approaches to attain a globally optimal strategy. To address these challenges, we propose a hierarchical graph Transformer framework called HGformer. By incorporating an enhanced graph Transformer encoder with structural biases and a two-agent hierarchical decision model, our approach enables efficient policy generation in large-scale adversarial environments. Moreover, we design a layer-by-layer feedback reinforcement learning algorithm that feeds the long-term returns from lower-level decisions back into the optimization of the higher-level strategy, thus bridging the coordination gap between the two decision-making stages. Experimental results demonstrate that, compared to existing hierarchical decision-making or graph neural network methods, HGformer significantly improves resource allocation efficiency and adversarial payoff, achieving superior overall performance in complex dynamic game scenarios.

In sequential decision-making problems, Return-Conditioned Supervised Learning (RCSL) has gained increasing recognition for its simplicity and stability in modern decision-making tasks. Unlike traditional offline reinforcement learning (RL) algorithms, RCSL frames policy learning as a supervised learning problem by taking both the state and return as input. This approach eliminates the instability often associated with temporal difference (TD) learning in offline RL. However, RCSL has been criticized for lacking the stitching property, meaning its performance is inherently limited by the quality of the policy used to generate the offline dataset. To address this limitation, we propose a principled and simple framework called Reinforced RCSL. The key innovation of our framework is the introduction of a concept we call the in-distribution optimal return-to-go. This mechanism leverages our policy to identify the best achievable in-dataset future return based on the current state, avoiding the need for complex return augmentation techniques. Our theoretical analysis demonstrates that Reinforced RCSL can consistently outperform the standard RCSL approach. Empirical results further validate our claims, showing significant performance improvements across a range of benchmarks.

In this work, we introduce the Time-Aware World Model (TAWM), a model-based approach that explicitly incorporates temporal dynamics. By conditioning on the time-step size, Δt, and training over a diverse range of Δt values -- rather than sampling at a fixed time-step -- TAWM learns both high- and low-frequency task dynamics across diverse control problems. Grounded in the information-theoretic insight that the optimal sampling rate depends on a system's underlying dynamics, this time-aware formulation improves both performance and data efficiency. Empirical evaluations show that TAWM consistently outperforms conventional models across varying observation rates in a variety of control tasks, using the same number of training samples and iterations. Our code can be found online at: github.com/anh-nn01/Time-Aware-World-Model.

Offline Reinforcement Learning (RL) struggles with distributional shifts, leading to the $Q$-value overestimation for out-of-distribution (OOD) actions. Existing methods address this issue by imposing constraints; however, they often become overly conservative when evaluating OOD regions, which constrains the $Q$-function generalization. This over-constraint issue results in poor $Q$-value estimation and hinders policy improvement. In this paper, we introduce a novel approach to achieve better $Q$-value estimation by enhancing $Q$-function generalization in OOD regions within Convex Hull and its Neighborhood (CHN). Under the safety generalization guarantees of the CHN, we propose the Smooth Bellman Operator (SBO), which updates OOD $Q$-values by smoothing them with neighboring in-sample $Q$-values. We theoretically show that SBO approximates true $Q$-values for both in-sample and OOD actions within the CHN. Our practical algorithm, Smooth Q-function OOD Generalization (SQOG), empirically alleviates the over-constraint issue, achieving near-accurate $Q$-value estimation. On the D4RL benchmarks, SQOG outperforms existing state-of-the-art methods in both performance and computational efficiency.