Offline Multi-Agent Reinforcement Learning (MARL) is an emerging field that aims to learn optimal multi-agent policies from pre-collected datasets. Compared to single-agent case, multi-agent setting involves a large joint state-action space and coupled behaviors of multiple agents, which bring extra complexity to offline policy optimization. In this work, we revisit the existing offline MARL methods and show that in certain scenarios they can be problematic, leading to uncoordinated behaviors and out-of-distribution (OOD) joint actions. To address these issues, we propose a new offline MARL algorithm, named In-Sample Sequential Policy Optimization (InSPO). InSPO sequentially updates each agent's policy in an in-sample manner, which not only avoids selecting OOD joint actions but also carefully considers teammates' updated policies to enhance coordination. Additionally, by thoroughly exploring low-probability actions in the behavior policy, InSPO can well address the issue of premature convergence to sub-optimal solutions. Theoretically, we prove InSPO guarantees monotonic policy improvement and converges to quantal response equilibrium (QRE). Experimental results demonstrate the effectiveness of our method compared to current state-of-the-art offline MARL methods.

OpenAI o1 represents a significant milestone in Artificial Inteiligence, which achieves expert-level performances on many challanging tasks that require strong reasoning ability.OpenAI has claimed that the main techinique behinds o1 is the reinforcement learining. Recent works use alternative approaches like knowledge distillation to imitate o1's reasoning style, but their effectiveness is limited by the capability ceiling of the teacher model. Therefore, this paper analyzes the roadmap to achieving o1 from the perspective of reinforcement learning, focusing on four key components: policy initialization, reward design, search, and learning. Policy initialization enables models to develop human-like reasoning behaviors, equipping them with the ability to effectively explore solution spaces for complex problems. Reward design provides dense and effective signals via reward shaping or reward modeling, which is the guidance for both search and learning. Search plays a crucial role in generating high-quality solutions during both training and testing phases, which can produce better solutions with more computation. Learning utilizes the data generated by search for improving policy, which can achieve the better performance with more parameters and more searched data. Existing open-source projects that attempt to reproduce o1 can be seem as a part or a variant of our roadmap. Collectively, these components underscore how learning and search drive o1's advancement, making meaningful contributions to the development of LLM.

Managing mixed traffic comprising human-driven and robot vehicles (RVs) across large-scale networks presents unique challenges beyond single-intersection control. This paper proposes a reinforcement learning framework for coordinating mixed traffic across multiple interconnected intersections. Our key contribution is a neighbor-aware reward mechanism that enables RVs to maintain balanced distribution across the network while optimizing local intersection efficiency. We evaluate our approach using a real-world network, demonstrating its effectiveness in managing realistic traffic patterns. Results show that our method reduces average waiting times by 39.2% compared to the state-of-the-art single-intersection control policy and 79.8% compared to traditional traffic signals. The framework's ability to coordinate traffic across multiple intersections while maintaining balanced RV distribution provides a foundation for deploying learning-based solutions in urban traffic systems.

However, the intermittent nature of wind power introduces inherent variability and uncertainty when integrated into power systems. As the wind power penetration level increases, the secure and reliable operation of power systems becomes a significant challenge [1]. In practice, the grid usually requires the active power fluctuation from wind farms to be confined to a specific value within a one-minute time window [2]. Therefore, Wind Power smoothing control (PSC) has emerged as a potential solution. Previous research has established two major categories of Power Smoothing Control for wind farms, including regulation control of wind turbines and indirect power control by Battery Energy Storage System (BESS). The former approach typically involves pitch angle control [3], rotor inertia control [4], and Direct Current (DC)-link voltage control [5], which require a different operation from maximum power point tracking, causing inefficiency and potential damages [6]. On the contrary, with a stronger capability of power smoothing, the BESS-based PSC coordinates the active power from BESS and wind turbine [7], providing rapid response to power fluctuation with high operability and little power loss. Recognizing the benefits of such Wind Storage Integrated Systems (WSIS) [8], incentive policies have been introduced to mandate the installation of BESSs from 10% to 30% of wind farms' installed capacity. WSIS facilitates wind power storage, allocating, and smoothing, enhancing delivery stability and energy management flexibility for both the grid and wind farm.

Q-learning is a widely used reinforcement learning technique for solving path planning problems. It primarily involves the interaction between an agent and its environment, enabling the agent to learn an optimal strategy that maximizes cumulative rewards. Although many studies have reported the effectiveness of Q-learning, it still faces slow convergence issues in practical applications. To address this issue, we propose the NDR-QL method, which utilizes neural network outputs as heuristic information to accelerate the convergence process of Q-learning. Specifically, we improved the dual-output neural network model by introducing a start-end channel separation mechanism and enhancing the feature fusion process. After training, the proposed NDR model can output a narrowly focused optimal probability distribution, referred to as the guideline, and a broadly distributed suboptimal distribution, referred to as the region. Subsequently, based on the guideline prediction, we calculate the continuous reward function for the Q-learning method, and based on the region prediction, we initialize the Q-table with a bias. We conducted training, validation, and path planning simulation experiments on public datasets. The results indicate that the NDR model outperforms previous methods by up to 5\% in prediction accuracy. Furthermore, the proposed NDR-QL method improves the convergence speed of the baseline Q-learning method by 90\% and also surpasses the previously improved Q-learning methods in path quality metrics.

Link prediction in dynamic graphs (LPDG) has been widely applied to real-world applications such as website recommendation, traffic flow prediction, organizational studies, etc. These models are usually kept local and secure, with only the interactive interface restrictively available to the public. Thus, the problem of the black-box evasion attack on the LPDG model, where model interactions and data perturbations are restricted, seems to be essential and meaningful in practice. In this paper, we propose the first practicable black-box evasion attack method that achieves effective attacks against the target LPDG model, within a limited amount of interactions and perturbations. To perform effective attacks under limited perturbations, we develop a graph sequential embedding model to find the desired state embedding of the dynamic graph sequences, under a deep reinforcement learning framework. To overcome the scarcity of interactions, we design a multi-environment training pipeline and train our agent for multiple instances, by sharing an aggregate interaction buffer. Finally, we evaluate our attack against three advanced LPDG models on three real-world graph datasets of different scales and compare its performance with related methods under the interaction and perturbation constraints. Experimental results show that our attack is both effective and practicable.

We study the Lagrangian Index Policy (LIP) for restless multi-armed bandits with long-run average reward. In particular, we compare the performance of LIP with the performance of the Whittle Index Policy (WIP), both heuristic policies known to be asymptotically optimal under certain natural conditions. Even though in most cases their performances are very similar, in the cases when WIP shows bad performance, LIP continues to perform very well. We then propose reinforcement learning algorithms, both tabular and NN-based, to obtain online learning schemes for LIP in the model-free setting. The proposed reinforcement learning schemes for LIP requires significantly less memory than the analogous scheme for WIP. We calculate analytically the Lagrangian index for the restart model, which describes the optimal web crawling and the minimization of the weighted age of information. We also give a new proof of asymptotic optimality in case of homogeneous bandits as the number of arms goes to infinity, based on exchangeability and de Finetti's theorem.

Mechanical Ventilation (MV) is a critical life-support intervention in intensive care units (ICUs). However, optimal ventilator settings are challenging to determine because of the complexity of balancing patient-specific physiological needs with the risks of adverse outcomes that impact morbidity, mortality, and healthcare costs. This study introduces ConformalDQN, a novel distribution-free conformal deep Q-learning approach for optimizing mechanical ventilation in intensive care units. By integrating conformal prediction with deep reinforcement learning, our method provides reliable uncertainty quantification, addressing the challenges of Q-value overestimation and out-of-distribution actions in offline settings. We trained and evaluated our model using ICU patient records from the MIMIC-IV database. ConformalDQN extends the Double DQN architecture with a conformal predictor and employs a composite loss function that balances Q-learning with well-calibrated probability estimation. This enables uncertainty-aware action selection, allowing the model to avoid potentially harmful actions in unfamiliar states and handle distribution shifts by being more conservative in out-of-distribution scenarios. Evaluation against baseline models, including physician policies, policy constraint methods, and behavior cloning, demonstrates that ConformalDQN consistently makes recommendations within clinically safe and relevant ranges, outperforming other methods by increasing the 90-day survival rate. Notably, our approach provides an interpretable measure of confidence in its decisions, which is crucial for clinical adoption and potential human-in-the-loop implementations.

Reinforcement learning tasks in real-world scenarios often involve large, high-dimensional action spaces, leading to challenges such as convergence difficulties, instability, and high computational complexity. It is widely acknowledged that traditional value-based reinforcement learning algorithms struggle to address these issues effectively. A prevalent approach involves generating independent sub-actions within each dimension of the action space. However, this method introduces bias, hindering the learning of optimal policies. In this paper, we propose an advantage-based optimization method and an algorithm named Advantage Branching Dueling Q-network (ABQ). ABQ incorporates a baseline mechanism to tune the action value of each dimension, leveraging the advantage relationship across different sub-actions. With this approach, the learned policy can be optimized for each dimension. Empirical results demonstrate that ABQ outperforms BDQ, achieving 3%, 171%, and 84% more cumulative rewards in HalfCheetah, Ant, and Humanoid environments, respectively. Furthermore, ABQ exhibits competitive performance when compared against two continuous action benchmark algorithms, DDPG and TD3.

The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it's challenging to design reward functions for real-world tasks, especially for high-dimensional robotic control, due to complex relationships among joints and tasks. Recent advancements large language models (LLMs) enable automatic reward function design. However, approaches evaluate reward functions by re-training policies from scratch placing an undue burden on the reward function, expecting it to be effective throughout the whole policy improvement process. We argue for a more practical strategy in robotic autonomy, focusing on refining existing policies with policy-dependent reward functions rather than a universal one. To this end, we propose a novel reward-policy co-evolution framework where the reward function and the learned policy benefit from each other's progressive on-the-fly improvements, resulting in more efficient and higher-performing skill acquisition. Specifically, the reward evolution process translates the robot's previous best reward function, descriptions of tasks and environment into text inputs. These inputs are used to query LLMs to generate a dynamic amount of reward function candidates, ensuring continuous improvement at each round of evolution. For policy evolution, our method generates new policy populations by hybridizing historically optimal and random policies. Through an improved Bayesian optimization, our approach efficiently and robustly identifies the most capable and plastic reward-policy combination, which then proceeds to the next round of co-evolution. Despite using less data, our approach demonstrates an average normalized improvement of 95.3% across various high-dimensional robotic skill learning tasks.