This paper investigates infinite-horizon average reward Constrained Markov Decision Processes (CMDPs) under general parametrized policies with smooth and bounded policy gradients. We propose a Primal-Dual Natural Actor-Critic algorithm that adeptly manages constraints while ensuring a high convergence rate. In particular, our algorithm achieves global convergence and constraint violation rates of O(1/ T) over a horizon of length T when the mixing time, τmix, is known to the learner. In absence of knowledge of τmix, the achievable rates change to O(1/T0.5 ϵ) provided that T O τ2/ϵmix . Our results match the theoretical lower bound for Markov Decision Processes and establish a new benchmark in the theoretical exploration of average reward CMDPs.

Heterogeneity poses a fundamental challenge for many real-world large-scale decision-making problems but remains largely understudied. In this paper, we study the fully heterogeneous setting of a prominent class of such problems, known as weakly-coupled Markov decision processes (WCMDPs). Each WCMDP consists of N arms (or subproblems), which have distinct model parameters in the fully heterogeneous setting, leading to the curse of dimensionality when N is large. We show that, under mild assumptions, an efficiently computable policy achieves an O(1/ N) optimality gap in the long-run average reward per arm for fully heterogeneous WCMDPs as N becomes large. This is the first asymptotic optimality result for fully heterogeneous average-reward WCMDPs. Our main technical innovation is the construction of projection-based Lyapunov functions that certify the convergence of rewards and costs to an optimal region, even under full heterogeneity.1

Self-improvement via RL often fails on complex reasoning tasks because GRPOstyle post-training methods rely on the model's initial ability to generate positive samples. Without guided exploration, these approaches merely reinforce what the model already knows (distribution-sharpening) rather than enabling the model to solve problems where it initially generates no correct solutions. To unlock reasoning ability in such settings, the model must explore new reasoning trajectories beyond its current output distribution. Such exploration requires access to sufficiently good positive samples to guide the learning. While expert demonstrations seem like a natural solution, we find that they are often ineffective in RL post-training.

Despite its promise, imitation learning often fails in long-horizon environments where perfect replication of demonstrations is unrealistic and small errors can accumulate catastrophically. We introduce Cago (Capability-Aware Goal Sampling), a novel learning-from-demonstrations method that mitigates the brittle dependence on expert trajectories for direct imitation. Unlike prior methods that rely on demonstrations only for policy initialization or reward shaping, Cago dynamically tracks the agent's competence along expert trajectories and uses this signal to select intermediate steps--goals that are just beyond the agent's current reach--to guide learning. This results in an adaptive curriculum that enables steady progress toward solving the full task. Empirical results demonstrate that Cago significantly improves sample efficiency and final performance across a range of sparse-reward, goal-conditioned tasks, consistently outperforming existing learning from-demonstrations baselines.

One proposed mechanism to improve exploration in reinforcement learning is through the use of macro-actions. Paradoxically though, in many scenarios the naive addition of macro-actions does not lead to better exploration, but rather the opposite. It has been argued that this was caused by adding non-useful macros and multiple works have focused on mechanisms to discover effectively environmentspecific useful macros. In this work, we take a slightly different perspective. We argue that the difficulty stems from the trade-offs between reducing the average number of decisions per episode versus increasing the size of the action space. Namely, one typically treats each potential macro-action as independent and atomic, hence strictly increasing the search space and making typical exploration strategies inefficient. To address this problem we propose a novel regularization term that exploits the relationship between actions and macro-actions to improve the credit assignment mechanism by reducing the effective dimension of the action space and, therefore, improving exploration. The term relies on a similarity matrix that is meta-learned jointly with learning the desired policy.

Agents that understand objects and their interactions can learn policies that are more robust and transferable.

Recent text-to-image systems face limitations in handling multimodal inputs and complex reasoning tasks. We introduce MindOmni, a unified multimodal large language model that addresses these challenges by incorporating reasoning generation through reinforcement learning. MindOmni leverages a three-phase training strategy: i) design of a unified vision language model with a decoder-only diffusion module, ii) supervised fine-tuning with Chain-of-Thought (CoT) instruction data, and iii) our proposed Reasoning Generation Policy Optimization (RGPO) algorithm, utilizing multimodal feedback to effectively guide policy updates. Experimental results demonstrate that MindOmni outperforms existing models, achieving impressive performance on both understanding and generation benchmarks, meanwhile showcasing advanced fine-grained reasoning generation capabilities, especially with mathematical reasoning instruction.

Compiler auto-tuning optimizes pass sequences to improve performance metrics such as Intermediate Representation (IR) instruction count. Although recent advances leveraging Large Language Models (LLMs) have shown promise in automating compiler tuning, two significant challenges still remain: the absence of highquality reasoning datasets for agents training, and limited effective interactions with the compilation environment. In this work, we introduce Compiler-R1, the first reinforcement learning (RL)-driven framework specifically augmenting LLM capabilities for compiler auto-tuning. Compiler-R1 features a curated, high-quality reasoning dataset and a novel two-stage end-to-end RL training pipeline, enabling efficient environment exploration and learning through an outcome-based reward. Extensive experiments across seven datasets demonstrate Compiler-R1 achieving an average 8.46% IR instruction count reduction compared to opt -Oz, showcasing the strong potential of RL-trained LLMs for compiler optimization.

In this article, we present a robust $Q$-learning algorithm for discrete-time mean-field control problems under Wasserstein uncertainty in the common noise law. The algorithm combines a quantization-and-projection scheme with a Wasserstein dual reformulation on the common-noise space. We establish its convergence together with finite-time iteration bounds for both synchronous and asynchronous learning schemes. Numerical experiments on systemic risk and epidemic models compare the asynchronous implementation with an idealized Bellman iteration, illustrate the robustness-performance tradeoff under common-noise misspecification, and report the observed convergence behavior of the asynchronous $Q$-learning algorithm.

In offline Reinforcement Learning, immediate rewards in logged batch data are often unobserved due to sparse or irregular record-keeping, or censored beyond certain reward values. This issue arises in practical settings, including health care and marketing. We investigate off-policy evaluation (OPE) in finite-horizon Markov decision processes when rewards are missing not at random (MNAR), which breaks ignorability and induces selection bias even after conditioning on states and actions. To address this, we formalize a reward-dependent propensity model and use future states as shadow variables to identify the full-data conditional mean reward. We further introduce a bridge function that recovers the conditional mean reward without explicitly modeling the MNAR mechanism, and estimate it via a min-max procedure to avoid double sampling. Building upon these identification results, we propose an Fitted-Q-Evaluation-style estimator that propagates the recovered rewards while allowing target policies to depend on past missingness indicators. Finally, we establish consistency and finite-sample error bounds for our OPE estimator, and show through experiments the strong performance of our method compared to existing methods on simulated and MIMIC-III Sepsis data.