Inverse reinforcement learning (IRL) aims to explain observed behavior by uncovering an underlying reward. In the maximum-entropy or Gumbel-shocks-to-reward frameworks, this amounts to fitting a reward function and a soft value function that together satisfy the soft Bellman consistency condition and maximize the likelihood of observed actions. While this perspective has had enormous impact in imitation learning for robotics and understanding dynamic choices in economics, practical learning algorithms often involve delicate inner-loop optimization, repeated dynamic programming, or adversarial training, all of which complicate the use of modern, highly expressive function approximators like neural nets and boosting. We revisit softmax IRL and show that the population maximum-likelihood solution is characterized by a linear fixed-point equation involving the behavior policy. This observation reduces IRL to two off-the-shelf supervised learning problems: probabilistic classification to estimate the behavior policy, and iterative regression to solve the fixed point. The resulting method is simple and modular across function approximation classes and algorithms. We provide a precise characterization of the optimal solution, a generic oracle-based algorithm, finite-sample error bounds, and empirical results showing competitive or superior performance to MaxEnt IRL.

We propose CURE, a novel reinforcement learning framework with a dedicated reward design that co-evolves coding and unit test generation capabilities based on their interaction outcomes, without any ground-truth code as supervision. This approach enables flexible and scalable training and allows the unit tester to learn directly from the coder's mistakes. Our derived ReasonFlux-Coder-7B and 14B models improve code generation accuracy by 5.3% and Best-of-N accuracy by 9.0% after optimization on Qwen2.5-Instruct models, outperforming similarly sized Qwen-Coder, DeepSeek-Coder, and Seed-Coder. They naturally extend to downstream tasks such as test-time scaling and agentic coding-achieving a 8.1% improvement over the base model. For the long-CoT model, our ReasonFlux-Coder-4B consistently outperforms Qwen3-4B while achieving 64.8% inference efficiency in unit test generation. Notably, we also find that our model can serve as an effective reward model for reinforcement learning on base models. Project: https://github.com/Gen-Verse/CURE

Actor-critic methods constitute a central paradigm in reinforcement learning (RL), coupling policy evaluation with policy improvement. While effective across many domains, these methods rely on separate actor and critic networks, which makes training vulnerable to architectural decisions and hyperparameter tuning. Such complexity limits their scalability in settings that require large function approximators. Recently, diffusion models have recently been proposed as expressive policies that capture multi-modal behaviors and improve exploration, but they introduce additional design choices and computational burdens, hindering efficient deployment. We introduce Actor-Critic without Actor (ACA), a lightweight framework that eliminates the explicit actor network and instead generates actions directly from the gradient field of a noise-level critic. This design removes the algorithmic and computational overhead of actor training while keeping policy improvement tightly aligned with the critic's latest value estimates. Moreover, ACA retains the ability to capture diverse, multi-modal behaviors without relying on diffusion-based actors, combining simplicity with expressiveness. Through extensive experiments on standard online RL benchmarks,ACA achieves more favorable learning curves and competitive performance compared to both standard actor-critic and state-of-the-art diffusion-based methods, providing a simple yet powerful solution for online RL.

Human feedback can greatly accelerate robot learning, but in real-world settings, such feedback is costly and limited. Existing human-in-the-loop reinforcement learning (HiL-RL) methods often assume abundant feedback, limiting their practicality for physical robot deployment. In this work, we introduce SPARQ, a progress-aware query policy that requests feedback only when learning stagnates or worsens, thereby reducing unnecessary oracle calls. We evaluate SPARQ on a simulated UR5 cube-picking task in PyBullet, comparing against three baselines: no feedback, random querying, and always querying. Our experiments show that SPARQ achieves near-perfect task success, matching the performance of always querying while consuming about half the feedback budget. It also provides more stable and efficient learning than random querying, and significantly improves over training without feedback. These findings suggest that selective, progress-based query strategies can make HiL-RL more efficient and scalable for robots operating under realistic human effort constraints.

Metascheduling in time-triggered architectures has been crucial in adapting to dynamic and unpredictable environments, ensuring the reliability and efficiency of task execution. However, traditional approaches face significant challenges when training Artificial Intelligence (AI) scheduling inferences offline, particularly due to the complexities involved in constructing a comprehensive Multi-Schedule Graph (MSG) that accounts for all possible scenarios. The process of generating an MSG that captures the vast probability space, especially when considering context events like hardware failures, slack variations, or mode changes, is resource-intensive and often infeasible. To address these challenges, we propose an adaptive online learning unit integrated within the metascheduler to enhance performance in real-time. The primary motivation for developing this unit stems from the limitations of offline training, where the MSG created is inherently a subset of the complete space, focusing only on the most probable and critical context events. In the online mode, Reinforcement Learning (RL) plays a pivotal role by continuously exploring and discovering new scheduling solutions, thus expanding the MSG and enhancing system performance over time. This dynamic adaptation allows the system to handle unexpected events and complex scheduling scenarios more effectively. Several RL models were implemented within the online learning unit, each designed to address specific challenges in scheduling. These models not only facilitate the discovery of new solutions but also optimize existing schedulers, particularly when stricter deadlines or new performance criteria are introduced. By continuously refining the AI inferences through real-time training, the system remains flexible and capable of meeting evolving demands, thus ensuring robustness and efficiency in large-scale, safety-critical environments.

Generative flow networks utilize a flow-matching loss to learn a stochastic policy for generating objects from a sequence of actions, such that the probability of generating a pattern can be proportional to the corresponding given reward. However, a theoretical framework for multi-agent generative flow networks (MA-GFlowNets) has not yet been proposed. In this paper, we propose the theory framework of MA-GFlowNets, which can be applied to multiple agents to generate objects collaboratively through a series of joint actions. We further propose four algorithms: a centralized flow network for centralized training of MA-GFlowNets, an independent flow network for decentralized execution, a joint flow network for achieving centralized training with decentralized execution, and its updated conditional version. Joint Flow training is based on a local-global principle allowing to train a collection of (local) GFN as a unique (global) GFN. This principle provides a loss of reasonable complexity and allows to leverage usual results on GFN to provide theoretical guarantees that the independent policies generate samples with probability proportional to the reward function. Experimental results demonstrate the superiority of the proposed framework compared to reinforcement learning and MCMC-based methods.

Fuzzing is effective for vulnerability discovery but struggles with complex targets such as compilers, interpreters, and database engines, which accept textual input that must satisfy intricate syntactic and semantic constraints. Although language models (LMs) have attracted interest for this task due to their vast latent knowledge and reasoning potential, their practical adoption has been limited. The major challenges stem from insufficient exploration of deep program logic among real-world codebases, and the high cost of leveraging larger models. To overcome these challenges, we propose R1-Fuzz, the first framework that leverages reinforcement learning (RL) to specialize cost-efficient LMs and integrate them for complex textual fuzzing input generation. R1-Fuzz introduces two key designs: coverage-slicing-based question construction and a distance-based reward calculation. Through RL-based post-training of a model with our constructed dataset, R1-Fuzz designs a fuzzing workflow that tightly integrates LMs to reason deep program semantics during fuzzing. Evaluations on diverse real-world targets show that our design enables a small model, named R1-Fuzz-7B, to rival or even outperform much larger models in real-world fuzzing. Notably, R1-Fuzz achieves up to 75\% higher coverage than state-of-the-art fuzzers and discovers 29 previously unknown vulnerabilities, demonstrating its practicality.

Autonomous exploration in structured and complex indoor environments remains a challenging task, as existing methods often struggle to appropriately model unobserved space and plan globally efficient paths. To address these limitations, we propose GUIDE, a novel exploration framework that synergistically combines global graph inference with diffusion-based decision-making. We introduce a region-evaluation global graph representation that integrates both observed environmental data and predictions of unexplored areas, enhanced by a region-level evaluation mechanism to prioritize reliable structural inferences while discounting uncertain predictions. Building upon this enriched representation, a diffusion policy network generates stable, foresighted action sequences with significantly reduced denoising steps. Extensive simulations and real-world deployments demonstrate that GUIDE consistently outperforms state-of-the-art methods, achieving up to 18.3% faster coverage completion and a 34.9% reduction in redundant movements.

We draw an analogy between static friction in classical mechanics and extrapolation error in off-policy RL, and use it to formulate a constraint that prevents the policy from drifting toward unsupported actions. In this study, we present Frictional Q-learning, a deep reinforcement learning algorithm for continuous control, which extends batch-constrained reinforcement learning. Our algorithm constrains the agent's action space to encourage behavior similar to that in the replay buffer, while maintaining a distance from the manifold of the orthonormal action space. The constraint preserves the simplicity of batch-constrained, and provides an intuitive physical interpretation of extrapolation error. Empirically, we further demonstrate that our algorithm is robustly trained and achieves competitive performance across standard continuous control benchmarks.