NeurIPS 2025 Papers

Auction-based Federated Learning (AFL) fosters collaboration among self-interested data consumers (DCs) and data owners (DOs). A major challenge in AFL pertains to how DCs select and bid for DOs. Existing methods are generally static, making them ill-suited for dynamic AFL markets. To address this issue, we propose the R}einforcement Learning-based Bidding Strategy for DCs in Auction-based Federated Learning (RLB-AFL). We incorporate historical states into a Deep Q-Network to capture sequential information critical for bidding decisions. To mitigate state space sparsity, where specific states rarely reoccur for each DC during auctions, we incorporate the Gaussian Mixture Model into RLB-AFL. This facilitates soft clustering on sequential states, reducing the state space dimensionality and easing exploration and action-value function approximation. In addition, we enhance the $\epsilon$-greedy policy to help the RLB-AFL agent balance exploitation and exploration, enabling it to be more adaptable in the AFL decision-making process. Extensive experiments under 6 widely used benchmark datasets demonstrate that RLB-AFL achieves superior performance compared to 8 state-of-the-art approaches. It outperforms the best baseline by 10.56% and 3.15% in terms of average total utility

Efficient exploration remains one of the key open problems in reinforcement learning. Discovering novel states or transitions efficiently requires policies that effectively direct the agent away from regions of the state space that are already well explored. We introduce Novel Exploration via Orthogonality (NEO), an approach that automatically uncovers not only which regions of the environment are novel but also how to reach them by leveraging Laplacian representations. NEO uses the eigenvectors of a modified graph Laplacian to induce gradient flows from states that are frequently visited (less novel) to states that are seldom visited (more novel). We show that NEO’s modified Laplacian yields eigenvectors whose extreme values align with the most novel regions of the state space. We provide bounds for the eigenvalues of the modified Laplacian; and we show that the smoothest eigenvectors with real eigenvalues below certain thresholds provide guaranteed gradients to novel states for both undirected and directed graphs. In an empirical evaluation in online, incremental settings, NEO outperformed related state-of-the- art approaches, including eigen-options and cover options, in a large collection of undirected and directed domains with varying structures.

Many online learning applications adopt the stochastic bandit problem with a linear reward model, where the unknown parameter exhibits a succinct structure. We study minimax regret lower bounds which allow to know whether more efficient algorithms can be proposed. We introduce a general definition of succinctness and propose a novel framework for constructing minimax regret lower bounds based on an information-regret trade-off. When applied to entry-sparse vectors, our framework sharpens a recent lower bound by (Hao et al, NeurIPS 2020). We further apply our framework to derive novel results. To the best of our knowledge, we provide the first lower bounds for the group-sparse and low-rank matrix settings.

Constrained optimization provides a common framework for dealing with conflicting objectives in reinforcement learning (RL). In most of these settings, the objectives (and constraints) are expressed though the expected accumulated reward. However, this formulation neglects risky or even possibly catastrophic events at the tails of the reward distribution, and is often insufficient for high-stakes applications in which the risk involved in outliers is critical. In this work, we propose a framework for risk-aware constrained RL, which exhibits per-stage robustness properties jointly in reward values and time using optimized certainty equivalents (OCEs). Our framework ensures an exact equivalent to the original constrained problem within a parameterized strong Lagrangian duality framework under appropriate constraint qualifications, and yields a simple algorithmic recipe which can be wrapped around standard RL solvers, such as PPO. Lastly, we establish the convergence of the proposed algorithm and verify the risk-aware properties of our approach through several numerical experiments.

This paper investigates the computational complexity of reinforcement learning within a novel linear function approximation regime, termed partial $q^{\pi}$-realizability. In this framework, the objective is to learn an $\epsilon$-optimal policy with respect to a predefined policy set $\Pi$, under the assumption that all value functions corresponding to policies in $\Pi$ are linearly realizable. This framework adopts assumptions that are weaker than those in the $q^{\pi}$-realizability setting yet stronger than those in the q*-realizability setup. As a result, it provides a more practical model for reinforcement learning scenarios where function approximation naturally arise. We prove that learning an $\epsilon$-optimal policy in this newly defined setting is computationally hard. More specifically, we establish NP-hardness under a parameterized greedy policy set (i.e., argmax) and, further, show that—unless NP = RP—an exponential lower bound (exponential in feature vector dimension) holds when the policy set contains softmax policies, under the Randomized Exponential Time Hypothesis. Our hardness results mirror those obtained in the $q^*$-realizability settings, and suggest that computational difficulty persists even when the policy class $ \Pi $ is expanded beyond the optimal policy, reinforcing the unbreakable nature of the computational hardness result regarding partial $ q^{\pi} $-realizability under two important policy sets. To establish our negative result, our primary technical contribution is a reduction from two complexity problems, $\delta$-Max-3SAT and $\delta$-Max-3SAT($b$), to instances of our problem settings: GLinear-$\kappa$-RL (under the greedy policy set) and SLinear-$\kappa$-RL (under the softmax policy set), respectively. Our findings indicate that positive computational results are generally unattainable in the context of partial $ q^{\pi} $-realizability, in sharp contrast to the $ q^{\pi} $-realizability setting under a generative access model.

Model-based reinforcement learning (MBRL) hinges on a learned dynamics model whose errors can compound along imagined rollouts. We study how encouraging \emph{flatness} in the model’s training loss affects downstream control, and show that steering optimization toward flatter minima yields a better policy. Concretely, we integrate \emph{Sharpness-Aware Minimization} (SAM) into world-model training as a drop-in objective, leaving the planner and policy components unchanged. On the theory side, we derive PAC-Bayesian bounds that link first-order sharpness to the value-estimation gap and the performance gap between model-optimal and true-optimal policies, implying that flatter minima tighten both. Empirically, SAM reduces measured sharpness and value-prediction error and improves returns across HumanoidBench, Atari-100k, and high-DoF DeepMind Control tasks. Augmenting existing MBRL algorithms with SAM increases mean return, with especially large gains in settings with high dimensional state–action space. We further observe positive transfer across algorithms and input modalities, including a transformer-based world-model. These results position flat-minima training as a simple, general mechanism for more robust MBRL without architectural changes.

Offline safe reinforcement learning aims to learn policies that satisfy predefined safety constraints from static datasets. Existing sequence-model-based methods condition action generation on symmetric input tokens for return-to-go and cost-to-go, neglecting their intrinsic asymmetry: RTG serves as a flexible performance target, while CTG should represent a rigid safety boundary. This symmetric conditioning leads to unreliable constraint satisfaction, especially when encountering out-of-distribution cost trajectories. To address this, we propose Boundary-to-Region (B2R), a framework that enables asymmetric conditioning through cost signal realignment . B2R redefines CTG as a boundary constraint under a fixed safety budget, unifying the cost distribution of all feasible trajectories while preserving reward structures. Combined with rotary positional embeddings , it enhances exploration within the safe region. Experimental results show that B2R satisfies safety constraints in 35 out of 38 safety-critical tasks while achieving superior reward performance over baseline methods. This work highlights the limitations of symmetric token conditioning and establishes a new theoretical and practical approach for applying sequence models to safe RL.

The challenge of learning with noisy labels is significant in machine learning, as it can severely degrade the performance of prediction models if not addressed properly. This paper introduces a novel framework that conceptualizes noisy label correction as a reinforcement learning (RL) problem. The proposed approach, Reinforcement Learning for Noisy Label Correction (RLNLC), defines a comprehensive state space representing data and their associated labels, an action space that indicates possible label corrections, and a reward mechanism that evaluates the efficacy of label corrections. RLNLC learns a deep feature representation based policy network to perform label correction through reinforcement learning, utilizing an actor-critic method. The learned policy is subsequently deployed to iteratively correct noisy training labels and facilitate the training of the prediction model. The effectiveness of RLNLC is demonstrated through extensive experiments on multiple benchmark datasets, where it consistently outperforms existing state-of-the-art techniques for learning with noisy labels.

We study the problem of offline imitation learning in Markov decision processes (MDPs), where the goal is to learn a well-performing policy given a dataset of state-action pairs generated by an expert policy. Complementing a recent line of work on this topic that assumes that the expert policy belongs to a tractable class of known policies, we approach this problem from a new angle and leverage another type of structural assumption about the environment. Specifically, for the class of linear $Q^\pi$-realizable MDPs, we introduce a new algorithm called primal-dual offline imitation learning (PDOIL), which is guaranteed to match the performance of any expert up to an additive error $\varepsilon$ with access to $\mathcal{O}(\varepsilon^{-2})$ samples. Moreover, we extend this result to possibly non-linear $Q^\pi$-realizable MDPs at the cost of a worst sample complexity of order $\mathcal{O}(\varepsilon^{-4})$. Finally, our analysis suggests a new loss function for training critic networks from expert data in deep imitation learning. Empirical evaluations on standard benchmarks demonstrate that the neural net implementation of PDOIL is superior to behavior cloning and competitive with state-of-the-art algorithms.

Model-free reinforcement learning (RL) combined with diffusion models has achieved significant progress in addressing complex continuous control tasks. However, a persistent challenge in RL remains the accurate estimation of Q-values, which critically governs the efficacy of policy optimization. Although recent advances employ parametric distributions to model value distributions for enhanced estimation accuracy, current methodologies predominantly rely on unimodal Gaussian assumptions or quantile representations. These constraints introduce distributional bias between the learned and true value distributions, particularly in some tasks with a nonstationary policy, ultimately degrading performance. To address these limitations, we propose value diffusion reinforcement learning (VDRL), a novel model-free online RL method that utilizes the generative capacity of diffusion models to represent multimodal value distributions. The core innovation of VDRL lies in the use of the variational loss of diffusion-based value distribution, which is theoretically proven to be a tight lower bound for the optimization objective under the KL-divergence measurement. Furthermore, we introduce double value diffusion learning with sample selection to enhance training stability and further improve value estimation accuracy. Extensive experiments conducted on the MuJoCo benchmark demonstrate that VDRL significantly outperforms some SOTA model-free online RL baselines, showcasing its effectiveness and robustness.

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 high-quality 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. Our code and datasets are publicly available at https://github.com/Panhaolin2001/Compiler-R1.

To learn approximately optimal acting policies for decision problems, modern Actor Critic algorithms rely on deep Neural Networks (DNNs) to parameterize the acting policy and greedification operators to iteratively improve it. The reliance on DNNs suggests an improvement that is gradient based, which is per step much less greedy than the improvement possible by greedier operators such as the greedy update used by Q-learning algorithms. On the other hand, slow and steady changes to the policy can also be beneficial for the stability of the learning process, resulting in a tradeoff between greedification and stability. To address this tradeoff, we propose to extend the standard framework of actor critic algorithms with value-improvement: a second greedification operator applied only when updating the policy's value estimate. In this framework the agent can evaluate non-parameterized policies and perform much greedier updates while maintaining the steady gradient-based improvement to the parameterized acting policy. We prove that this approach converges in the popular analysis scheme of generalized Policy Iteration in the finite-horizon domain. Empirically, incorporating value-improvement into the popular off-policy actor-critic algorithms TD3 and SAC significantly improves or matches performance over their respective baselines, across different environments from the DeepMind continuous control domain, with negligible compute and implementation cost.

The remarkable empirical performance of distributional reinforcement learning~(RL) has garnered increasing attention to understanding its theoretical advantages over classical RL. By decomposing the categorical distributional loss commonly employed in distributional RL, we find that the potential superiority of distributional RL can be attributed to a derived distribution-matching entropy regularization. This less-studied entropy regularization aims to capture additional knowledge of return distribution beyond only its expectation, contributing to an augmented reward signal in policy optimization. In contrast to the vanilla entropy regularization in MaxEnt RL, which explicitly encourages exploration by promoting diverse actions, the novel entropy regularization derived from categorical distributional loss implicitly updates policies to align the learned policy with (estimated) environmental uncertainty. Finally, extensive experiments verify the significance of this uncertainty-aware regularization from distributional RL on the empirical benefits over classical RL. Our study offers an innovative exploration perspective to explain the intrinsic benefits of distributional learning in RL.

Offline reinforcement learning (RL) aims to learn optimal policies from static datasets while enhancing generalization to out-of-distribution (OOD) data. To mitigate overfitting to suboptimal behaviors in offline datasets, existing methods often relax constraints on policy and data or extract informative patterns through data-driven techniques. However, there has been limited exploration into structurally guiding the optimization process toward flatter regions of the solution space that offer better generalization. Motivated by this observation, we present \textit{FANS}, a generalization-oriented structured network framework that promotes flatter and robust policy learning by guiding the optimization trajectory through modular architectural design. FANS comprises four key components: (1) Residual Blocks, which facilitate compact and expressive representations; (2) Gaussian Activation, which promotes smoother gradients; (3) Layer Normalization, which mitigates overfitting; and (4) Ensemble Modeling, which reduces estimation variance. By integrating FANS into a standard actor-critic framework, we highlight that this remarkably simple architecture achieves superior performance across various tasks compared to many existing advanced methods. Moreover, we validate the effectiveness of FANS in mitigating overestimation and promoting generalization, demonstrating the promising potential of architectural design in advancing offline RL.

State entropy regularization has empirically shown better exploration and sample complexity in reinforcement learning (RL). However, its theoretical guarantees have not been studied. In this paper, we show that state entropy regularization improves robustness to structured and spatially correlated perturbations. These types of variation are common in transfer learning but often overlooked by standard robust RL methods, which typically focus on small, uncorrelated changes. We provide a comprehensive characterization of these robustness properties, including formal guarantees under reward and transition uncertainty, as well as settings where the method performs poorly. Much of our analysis contrasts state entropy with the widely used policy entropy regularization, highlighting their different benefits. Finally, from a practical standpoint, we illustrate that compared with policy entropy, the robustness advantages of state entropy are more sensitive to the number of rollouts used for policy evaluation.

Offline reinforcement learning (RL) suffers from extrapolation errors induced by out-of-distribution (OOD) actions. To address this, offline RL algorithms typically impose constraints on action selection, which can be systematically categorized into density, support, and sample constraints. However, we show that each category has inherent limitations: density and sample constraints tend to be overly conservative in many scenarios, while the support constraint, though least restrictive, faces challenges in accurately modeling the behavior policy. To overcome these limitations, we propose a new neighborhood constraint that restricts action selection in the Bellman target to the union of neighborhoods of dataset actions. Theoretically, the constraint not only bounds extrapolation errors and distribution shift under certain conditions, but also approximates the support constraint without requiring behavior policy modeling. Moreover, it retains substantial flexibility and enables pointwise conservatism by adapting the neighborhood radius for each data point. In practice, we employ data quality as the adaptation criterion and design an adaptive neighborhood constraint. Building on an efficient bilevel optimization framework, we develop a simple yet effective algorithm, Adaptive Neighborhood-constrained Q learning (ANQ), to perform Q learning with target actions satisfying this constraint. Empirically, ANQ achieves state-of-the-art performance on standard offline RL benchmarks and exhibits strong robustness in scenarios with noisy or limited data.

Reinforcement Learning (RL) is a continuously growing field that has the potential to revolutionize many areas of artificial intelligence. However, despite its promise, RL research is often hindered by the lack of standardization in environment and algorithm implementations. This makes it difficult for researchers to compare and build upon each other's work, slowing down progress in the field. Gymnasium is an open-source library that provides a standard API for RL environments, aiming to tackle this issue. Gymnasium's main feature is a set of abstractions that allow for wide interoperability between environments and training algorithms, making it easier for researchers to develop and test RL algorithms. In addition, Gymnasium provides a collection of easy-to-use environments, tools for easily customizing environments, and tools to ensure the reproducibility and robustness of RL research. Through this unified framework, Gymnasium significantly streamlines the process of developing and testing RL algorithms, enabling researchers to focus more on innovation and less on implementation details. By providing a standardized platform for RL research, Gymnasium helps to drive forward the field of reinforcement learning and unlock its full potential. Gymnasium is available online at \url{https://github.com/Farama-Foundation/Gymnasium}.

We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative preference queries to identify the underlying reward while ensuring theoretical guarantees. We propose a meta-algorithm based on randomized exploration, which avoids the computational challenges associated with optimistic approaches and remains tractable. We establish both regret and last-iterate guarantees under mild reinforcement learning oracle assumptions. To improve query complexity, we introduce and analyze an improved algorithm that collects batches of trajectory pairs and applies optimal experimental design to select informative comparison queries. The batch structure also enables parallelization of preference queries, which is relevant in practical deployment as feedback can be gathered concurrently. Empirical evaluation confirms that the proposed method is competitive with reward-based reinforcement learning while requiring a small number of preference queries.

Reinforcement learning (RL) has recently demonstrated strong potential in enhancing the reasoning capabilities of large language models (LLMs). Particularly, the "Zero" reinforcement learning introduced by Deepseek-R1-Zero, enables direct RL training of base LLMs without relying on an intermediate supervised fine-tuning stage. Despite these advancements, current works for LLM reasoning mainly focus on mathematical and coding domains, largely due to data abundance and the ease of answer verification. This limits the applicability and generalization of such models to broader domains, where questions often have diverse answer representations, and data is more scarce. In this paper, we propose General-Reasoner, a novel training framework designed to enhance LLM reasoning capabilities across diverse domains. Our key contributions include: (1) constructing a large-scale, high-quality dataset of questions with verifiable answers curated by web crawling, covering a wide range of disciplines; and (2) developing a generative model-based answer verifier, which replaces traditional rule-based verification with the capability of chain-of-thought and context-awareness. We train a series of models and evaluate them on a wide range of datasets covering wide domains like physics, chemistry, finance, electronics etc. Our comprehensive evaluation across these 12 benchmarks (e.g. MMLU-Pro, GPQA, SuperGPQA, TheoremQA, BBEH and MATH AMC) demonstrates that General-Reasoner outperforms existing baseline methods, achieving robust and generalizable reasoning performance while maintaining superior effectiveness in mathematical reasoning tasks.