--Since the advent of autonomous driving technology, it has experienced remarkable progress over the last decade. However, most existing research still struggles to address the challenges posed by environments where multiple vehicles have to interact seamlessly. This study aims to integrate causal learning with reinforcement learning-based methods by leveraging causal disentanglement representation learning (CDRL) to identify and extract causal features that influence optimal decision-making in autonomous vehicles. These features are then incorporated into graph neural network-based reinforcement learning algorithms to enhance decision-making in complex traffic scenarios. By using causal features as inputs, the proposed approach enables the optimization of vehicle behavior at an unsignalized intersection. Experimental results demonstrate that our proposed method achieves the highest average reward during training and our approach significantly outperforms other learning-based methods in several key metrics such as collision rate and average cumulative reward during testing. This study provides a promising direction for advancing multi-agent autonomous driving systems and make autonomous vehicles' navigation safer and more efficient in complex traffic environments. ITH the advanced development in autonomous driving technologies, modern transportation has been gradually reshaped, paving the way for safer, more efficient, and environmentally sustainable mobility solutions. Effective decision-making is essential for autonomous vehicles to navigate complex environments, interact with human-driven vehicles (HVs), and respond appropriately to unknown situations.

Offline reinforcement learning (offline RL) offers a promising framework for developing control strategies in chemical process systems using historical data, without the risks or costs of online experimentation. This work investigates the application of offline RL to the safe and efficient control of an exothermic polymerisation continuous stirred-tank reactor. We introduce a Gymnasium-compatible simulation environment that captures the reactor's nonlinear dynamics, including reaction kinetics, energy balances, and operational constraints. The environment supports three industrially relevant scenarios: startup, grade change down, and grade change up. It also includes reproducible offline datasets generated from proportional-integral controllers with randomised tunings, providing a benchmark for evaluating offline RL algorithms in realistic process control tasks. We assess behaviour cloning and implicit Q-learning as baseline algorithms, highlighting the challenges offline agents face, including steady-state offsets and degraded performance near setpoints. To address these issues, we propose a novel deployment-time safety layer that performs gradient-based action correction using input convex neural networks (PICNNs) as learned cost models. The PICNN enables real-time, differentiable correction of policy actions by descending a convex, state-conditioned cost surface, without requiring retraining or environment interaction. Experimental results show that offline RL, particularly when combined with convex action correction, can outperform traditional control approaches and maintain stability across all scenarios. These findings demonstrate the feasibility of integrating offline RL with interpretable and safety-aware corrections for high-stakes chemical process control, and lay the groundwork for more reliable data-driven automation in industrial systems.

We propose novel classical and quantum online algorithms for learning finite-horizon and infinite-horizon average-reward Markov Decision Processes (MDPs). Our algorithms are based on a hybrid exploration-generative reinforcement learning (RL) model wherein the agent can, from time to time, freely interact with the environment in a generative sampling fashion, i.e., by having access to a "simulator". By employing known classical and new quantum algorithms for approximating optimal policies under a generative model within our learning algorithms, we show that it is possible to avoid several paradigms from RL like "optimism in the face of uncertainty" and "posterior sampling" and instead compute and use optimal policies directly, which yields better regret bounds compared to previous works. For finite-horizon MDPs, our quantum algorithms obtain regret bounds which only depend logarithmically on the number of time steps $T$, thus breaking the $O(\sqrt{T})$ classical barrier. This matches the time dependence of the prior quantum works of Ganguly et al. (arXiv'23) and Zhong et al. (ICML'24), but with improved dependence on other parameters like state space size $S$ and action space size $A$. For infinite-horizon MDPs, our classical and quantum bounds still maintain the $O(\sqrt{T})$ dependence but with better $S$ and $A$ factors. Nonetheless, we propose a novel measure of regret for infinite-horizon MDPs with respect to which our quantum algorithms have $\operatorname{poly}\log{T}$ regret, exponentially better compared to classical algorithms. Finally, we generalise all of our results to compact state spaces.

APR (Automated Program Repair) aims to automatically locate program defects, generate patches and validate the repairs. Existing techniques for APR are often combined with LLMs (Large Language Models), which leverages the code-related knowledge of LLMs to improve repair effectiveness. Current LLM-based APR methods typically utilize test cases only during the inference stage, adopting an iterative approach that performs repair first and validates it through test execution afterward. This conventional paradigm neglects two important aspects: the potential contribution of test cases in the training phase, and the possibility of leveraging testing prior to repair. To address this, we propose Repair-R1, which introduces test cases into the model's training phase and shifts test generation to precede repair. The model is required to first generate discriminative test cases that can distinguish defective behaviors, and then perform repair based on these tests. This enables the model to better locate defects and understand the underlying causes of defects, thereby improving repair effectiveness. We implement Repair-R1 with three different backbone models, using RL (reinforcement learning) to co-optimize test generation and bug repair. Experimental results on four widely adopted benchmarks demonstrate the superiority of Repair-R1. Specially, compared to vanilla models, Repair-R1 improves repair success rate by 2.68\% to 48.29\%, test generation success rate by 16.38\% to 53.28\%, and test coverage by 0.78\% to 53.96\%. We publish the code and weights at https://github.com/Tomsawyerhu/APR-RL and https://huggingface.co/tomhu/Qwen3-4B-RL-5000-step.

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success often reinforce flawed or inefficient reasoning paths, a problem we term inefficient exploration. This leads to agents that are brittle and fail to generalize, as they learn to find solutions without learning how to reason coherently. To address this, we introduce RLVMR, a novel framework that integrates dense, process-level supervision into end-to-end RL by rewarding verifiable, meta-reasoning behaviors. RLVMR equips an agent to explicitly tag its cognitive steps, such as planning, exploration, and reflection, and provides programmatic, rule-based rewards for actions that contribute to effective problem-solving. These process-centric rewards are combined with the final outcome signal and optimized using a critic-free policy gradient method. On the challenging ALFWorld and ScienceWorld benchmarks, RLVMR achieves new state-of-the-art results, with our 7B model reaching an 83.6% success rate on the most difficult unseen task split. Our analysis confirms these gains stem from improved reasoning quality, including significant reductions in redundant actions and enhanced error recovery, leading to more robust, efficient, and interpretable agents.

Reducing hallucinations in abstractive summarization remains a critical challenge for deploying language models (LMs) in real-world settings. In this work, we introduce a rewarddriven fine-tuning framework that explicitly optimizes for Entity Hallucination Index (EHI), a metric designed to quantify the presence, correctness, and grounding of named entities in generated summaries. Given a corpus of meeting transcripts, we first generate baseline summaries using a pre-trained LM and compute EHI scores via automatic entity extraction and matching. We then apply reinforcement learning to fine-tune the model parameters, using EHI as a reward signal to bias generation toward entity-faithful outputs. Our approach does not rely on human-written factuality annotations, enabling scalable fine-tuning. Experiments demonstrate consistent improvements in EHI across datasets, with qualitative analysis revealing a significant reduction in entity-level hallucinations without degradation in fluency or informativeness. We release a reproducible Colab pipeline, facilitating further research on hallucination-aware model fine-tuning using lightweight, hallucintion metrics like EHI.

The tension between data privacy and model utility has become the defining bottleneck for the practical deployment of large language models (LLMs) trained on sensitive corpora including healthcare. Differentially private stochastic gradient descent (DP-SGD) guarantees formal privacy, yet it does so at a pronounced cost: gradients are forcibly clipped and perturbed with noise, degrading sample efficiency and final accuracy. Numerous variants have been proposed to soften this trade-off, but they all share a handicap: their control knobs are hard-coded, global, and oblivious to the evolving optimization landscape. Consequently, practitioners are forced either to over-spend privacy budget in pursuit of utility, or to accept mediocre models in order to stay within privacy constraints. We present RLDP, the first framework to cast DP optimization itself as a closed-loop control problem amenable to modern deep reinforcement learning (RL). RLDP continuously senses rich statistics of the learning dynamics and acts by selecting fine-grained per parameter gradient-clipping thresholds as well as the magnitude of injected Gaussian noise. A soft actor-critic (SAC) hyper-policy is trained online during language model fine-tuning; it learns, from scratch, how to allocate the privacy budget where it matters and when it matters. Across more than 1,600 ablation experiments on GPT2-small, Llama-1B, Llama-3B, and Mistral-7B, RLDP delivers perplexity reductions of 1.3-30.5% (mean 5.4%) and an average 5.6% downstream utility gain. RLDP reaches each baseline's final utility after only 13-43% of the gradient-update budget (mean speed-up 71%), all while honoring the same ($ε$, $δ$)-DP contract and exhibiting equal or lower susceptibility to membership-inference and canary-extraction attacks.

A RL (Reinforcement Learning) algorithm was developed for command automation onboard a 3U CubeSat. This effort focused on the implementation of macro control action RL, a technique in which an onboard agent is provided with compiled information based on live telemetry as its observation. The agent uses this information to produce high-level actions, such as adjusting attitude to solar pointing, which are then translated into control algorithms and executed through lower-level instructions. Once trust in the onboard agent is established, real-time environmental information can be leveraged for faster response times and reduced reliance on ground control. The approach not only focuses on developing an RL algorithm for a specific satellite but also sets a precedent for integrating trusted AI into onboard systems. This research builds on previous work in three areas: (1) RL algorithms for issuing high-level commands that are translated into low-level executable instructions; (2) the deployment of AI inference models interfaced with live operational systems, particularly onboard spacecraft; and (3) strategies for building trust in AI systems, especially for remote and autonomous applications. Existing RL research for satellite control is largely limited to simulation-based experiments; in this work, these techniques are tailored by constructing a digital twin of a specific spacecraft and training the RL agent to issue macro actions in this simulated environment. The policy of the trained agent is copied to an isolated environment, where it is fed compiled information about the satellite to make inference predictions, thereby demonstrating the RL algorithm's validity on orbit without granting it command authority. This process enables safe comparison of the algorithm's predictions against actual satellite behavior and ensures operation within expected parameters.

A drone trajectory planner should be able to dynamically adjust the safety-efficiency trade-off according to varying mission requirements in unknown environments. Although traditional polynomial-based planners offer computational efficiency and smooth trajectory generation, they require expert knowledge to tune multiple parameters to adjust this trade-off. Moreover, even with careful tuning, the resulting adjustment may fail to achieve the desired trade-off. Similarly, although reinforcement learning-based planners are adaptable in unknown environments, they do not explicitly address the safety-efficiency trade-off. To overcome this limitation, we introduce a Decision Transformer-based trajectory planner that leverages a single parameter, Return-to-Go (RTG), as a \emph{temperature parameter} to dynamically adjust the safety-efficiency trade-off. In our framework, since RTG intuitively measures the safety and efficiency of a trajectory, RTG tuning does not require expert knowledge. We validate our approach using Gazebo simulations in both structured grid and unstructured random environments. The experimental results demonstrate that our planner can dynamically adjust the safety-efficiency trade-off by simply tuning the RTG parameter. Furthermore, our planner outperforms existing baseline methods across various RTG settings, generating safer trajectories when tuned for safety and more efficient trajectories when tuned for efficiency. Real-world experiments further confirm the reliability and practicality of our proposed planner.

Allocating mobility resources (e.g., shared bikes/e-scooters, ride-sharing vehicles) is crucial for rebalancing the mobility demand and supply in the urban environments. We propose in this work a novel multi-agent reinforcement learning named Hierarchical Adaptive Grouping-based Parameter Sharing (HAG-PS) for dynamic mobility resource allocation. HAG-PS aims to address two important research challenges regarding multi-agent reinforcement learning for mobility resource allocation: (1) how to dynamically and adaptively share the mobility resource allocation policy (i.e., how to distribute mobility resources) across agents (i.e., representing the regional coordinators of mobility resources); and (2) how to achieve memory-efficient parameter sharing in an urban-scale setting. To address the above challenges, we have provided following novel designs within HAG-PS. To enable dynamic and adaptive parameter sharing, we have designed a hierarchical approach that consists of global and local information of the mobility resource states (e.g., distribution of mobility resources). We have developed an adaptive agent grouping approach in order to split or merge the groups of agents based on their relative closeness of encoded trajectories (i.e., states, actions, and rewards). We have designed a learnable identity (ID) embeddings to enable agent specialization beyond simple parameter copy. We have performed extensive experimental studies based on real-world NYC bike sharing data (a total of more than 1.2 million trips), and demonstrated the superior performance (e.g., improved bike availability) of HAG-PS compared with other baseline approaches.