In an era where tool-augmented AI agents are becoming increasingly vital, our findings highlight the ability of Group Relative Policy Optimization (GRPO) to empower SLMs, which are traditionally constrained in tool use. The ability to use tools effectively has become a defining feature of Large Language Models (LLMs), allowing them to access external data and internal resources. As AI agents grow more sophisticated, tool-use capabilities have become indispensable. While LLMs have made significant progress in this area, Small Language Models (SLMs) still face challenges in accurately integrating tool use, especially in resource-constrained settings. This study investigates how Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), can enhance the tool-use accuracy of SLMs. By designing a well-defined reward system that reinforces structured JSON output, correct tool selection, and precise parameter usage, we demonstrate that GRPO enables SLMs to achieve significant improvements in tool-use capabilities (function calling/JSON output). Our approach provides a computationally efficient training method that enhances SLMs practical deployment in real-world AI applications.

Sparse-reward reinforcement learning (RL) remains fundamentally hard: without structure, any agent needs Ω(|S||A|/p) samples to recover rewards. We introduce Policy-A ware Matrix Completion (P AMC) as a first concrete step toward a structural reward learning framework. Our key idea is to exploit approximate low-rank + sparse structure in the reward matrix, under policy-biased (MNAR) sampling. We prove recovery guarantees with inverse-propensity weighting, and establish a visitation-weighted error-to-regret bound linking completion error to control performance. Importantly, when assumptions weaken, P AMC degrades gracefully: confidence intervals widen and the algorithm abstains, ensuring safe fallback to exploration. Empirically, P AMC improves sample efficiency across Atari-26 (10M steps), DM Control, MetaWorld MT50, D4RL offline RL, and preference-based RL benchmarks, outperforming DrQ-v2, DreamerV3, Agent57, T -REX/D-REX, and PrefPPO under compute-normalized comparisons. Our results highlight P AMC as a practical and principled tool when structural rewards exist, and as a concrete first instantiation of a broader structural reward learning perspective. What fundamental properties of reward functions determine the sample complexity of reinforcement learning?

Imitation learning advances robot capabilities by enabling the acquisition of diverse behaviors from human demonstrations. However, large-scale datasets used for policy training often introduce substantial variability in quality, which can negatively impact performance. As a result, automatically curating datasets by filtering low-quality samples to improve quality becomes essential. Existing robotic curation approaches rely on costly manual annotations and perform curation at a coarse granularity, such as the dataset or trajectory level, failing to account for the quality of individual state-action pairs. To address this, we introduce SCIZOR, a self-supervised data curation framework that filters out low-quality state-action pairs to improve the performance of imitation learning policies. SCIZOR targets two complementary sources of low-quality data: suboptimal data, which hinders learning with undesirable actions, and redundant data, which dilutes training with repetitive patterns. SCIZOR leverages a self-supervised task progress predictor for suboptimal data to remove samples lacking task progression, and a deduplication module operating on joint state-action representation for samples with redundant patterns. Empirically, we show that SCIZOR enables imitation learning policies to achieve higher performance with less data, yielding an average improvement of 15.4% across multiple benchmarks. More information is available at: https://ut-austin-rpl.github.io/SCIZOR/

A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, like Q-learning, allow learners to make optimal decisions based on past experiences. This paper studies off-policy learning from biased data in complex and high-dimensional domains where \emph{unobserved confounding} cannot be ruled out a priori. Building on the well-celebrated Deep Q-Network (DQN), we propose a novel deep reinforcement learning algorithm robust to confounding biases in observed data. Specifically, our algorithm attempts to find a safe policy for the worst-case environment compatible with the observations. We apply our method to twelve confounded Atari games, and find that it consistently dominates the standard DQN in all games where the observed input to the behavioral and target policies mismatch and unobserved confounders exist.

Abstract--The complexity of large-scale 6G-and-beyond networks demands innovative approaches for multi-objective optimization over vast search spaces, a task often intractable. Quantum computing (QC) emerges as a promising technology for efficient large-scale optimization. We present our vision of leveraging QC to tackle key classes of problems in future mobile networks. By analyzing and identifying common features, particularly their graph-centric representation, we propose a unified strategy involving QC algorithms. Specifically, we outline a methodology for optimization using quantum annealing as well as quantum reinforcement learning. Additionally, we discuss the main challenges that QC algorithms and hardware must overcome to effectively optimize future networks. Quantum computing (QC) has rapidly emerged as a promising field, with its unparalleled potential to tackle problems typically intractable for classical computers. Quantum bits (qubits) leverage the principles of superposition, interference and entanglement to accelerate computations and open the door to previously unimaginable algorithms. This fundamental characteristic allows quantum computers to perform complex calculations at speeds exponentially faster than their classical counterparts in certain domains, enabling breakthroughs in fields such as cryptography, materials science, and artificial intelligence (AI). Developments in QC pave the way for novel solutions to intractable optimization problems and are expected to play a disruptive role in multiple industries.

This study presents a novel reinforcement learning (RL)-based control framework aimed at enhancing the safety and robustness of the quadcopter, with a specific focus on resilience to in-flight one propeller failure. Addressing the critical need of a robust control strategy for maintaining a desired altitude for the quadcopter to safe the hardware and the payload in physical applications. The proposed framework investigates two RL methodologies Dynamic Programming (DP) and Deep Deterministic Policy Gradient (DDPG), to overcome the challenges posed by the rotor failure mechanism of the quadcopter. DP, a model-based approach, is leveraged for its convergence guarantees, despite high computational demands, whereas DDPG, a model-free technique, facilitates rapid computation but with constraints on solution duration. The research challenge arises from training RL algorithms on large dimensions and action domains. With modifications to the existing DP and DDPG algorithms, the controllers were trained not only to cater for large continuous state and action domain and also achieve a desired state after an inflight propeller failure. To verify the robustness of the proposed control framework, extensive simulations were conducted in a MATLAB environment across various initial conditions and underscoring its viability for mission-critical quadcopter applications. A comparative analysis was performed between both RL algorithms and their potential for applications in faulty aerial systems.

IQM Germany Abstract--Quantum policy evaluation (QPE) is a reinforcement learning (RL) algorithm which is quadratically more efficient than an analogous classical Monte Carlo estimation. It makes use of a direct quantum mechanical realization of a finite Markov decision process, in which the agent and the environment are modeled by unitary operators and exchange states, actions, and rewards in superposition. Previously, the quantum environment has been implemented and parametrized manually for an illustrative benchmark using a quantum simulator . In this paper, we demonstrate how these environment parameters can be learned from a batch of classical observational data through quantum machine learning (QML) on quantum hardware. The learned quantum environment is then applied in QPE to also compute policy evaluations on quantum hardware. Our experiments reveal that, despite challenges such as noise and short coherence times, the integration of QML and QPE shows promising potential for achieving quantum advantage in RL.

In time-critical settings such as assistive driving, assistants often rely on alerts or haptic signals to prompt rapid human attention, but these cues usually leave humans to interpret situations and decide responses independently, introducing potential delays or ambiguity in meaning. Language-based assistive systems can instead provide instructions backed by context, offering more informative guidance. However, current approaches (e.g., social assistive robots) largely prioritize content generation while overlooking critical timing factors such as verbal conveyance duration, human comprehension delays, and subsequent follow-through duration. These timing considerations are crucial in time-critical settings, where even minor delays can substantially affect outcomes. We aim to study this inherent trade-off between timeliness and informativeness by framing the challenge as a sequential decision-making problem using an augmented-state Markov Decision Process. We design a framework combining reinforcement learning and a generated offline taxonomy dataset, where we balance the trade-off while enabling a scalable taxonomy dataset generation pipeline. Empirical evaluation with synthetic humans shows our framework improves success rates by over 40% compared to methods that ignore time delays, while effectively balancing timeliness and informativeness. It also exposes an often-overlooked trade-off between these two factors, opening new directions for optimizing communication in time-critical human-AI assistance.

Autonomous driving has attracted great interest due to its potential capability in full-unsupervised driving. Model-based and learning-based methods are widely used in autonomous driving. Model-based methods rely on pre-defined models of the environment and may struggle with unforeseen events. Proximal policy optimization (PPO), an advanced learning-based method, can adapt to the above limits by learning from interactions with the environment. However, existing PPO faces challenges with poor training results, and low training efficiency in long sequences. Moreover, the poor training results are equivalent to collisions in driving tasks. To solve these issues, this paper develops an improved PPO by introducing the risk-aware mechanism, a risk-attention decision network, a balanced reward function, and a safety-assisted mechanism. The risk-aware mechanism focuses on highlighting areas with potential collisions, facilitating safe-driving learning of the PPO. The balanced reward function adjusts rewards based on the number of surrounding vehicles, promoting efficient exploration of the control strategy during training. Additionally, the risk-attention network enhances the PPO to hold channel and spatial attention for the high-risk areas of input images. Moreover, the safety-assisted mechanism supervises and prevents the actions with risks of collisions during the lane keeping and lane changing. Simulation results on a physical engine demonstrate that the proposed algorithm outperforms benchmark algorithms in collision avoidance, achieving higher peak reward with less training time, and shorter driving time remaining on the risky areas among multiple testing traffic flow scenarios.

Quadratic programming is a workhorse of modern nonlinear optimization, control, and data science. Although regularized methods offer convergence guarantees under minimal assumptions on the problem data, they can exhibit the slow tail-convergence typical of first-order schemes, thus requiring many iterations to achieve high-accuracy solutions. Moreover, hyperparameter tuning significantly impacts on the solver performance but how to find an appropriate parameter configuration remains an elusive research question. To address these issues, we explore how data-driven approaches can accelerate the solution process. Aiming at high-accuracy solutions, we focus on a stabilized interior-point solver and carefully handle its two-loop flow and control parameters. We will show that reinforcement learning can make a significant contribution to facilitating the solver tuning and to speeding up the optimization process. Numerical experiments demonstrate that, after a lightweight training, the learned policy generalizes well to different problem classes with varying dimensions and to various solver configurations.