Efficient traffic control (TSC) is essential for urban mobility, but traditional systems struggle to handle the complexity of real-world traffic. Multi-agent Reinforcement Learning (MARL) offers adaptive solutions, but online MARL requires extensive interactions with the environment, making it costly and impractical. Offline MARL mitigates these challenges by using historical traffic data for training but faces significant difficulties with heterogeneous behavior policies in real-world datasets, where mixed-quality data complicates learning. We introduce OffLight, a novel offline MARL framework designed to handle heterogeneous behavior policies in TSC datasets. To improve learning efficiency, OffLight incorporates Importance Sampling (IS) to correct for distributional shifts and Return-Based Prioritized Sampling (RBPS) to focus on high-quality experiences. OffLight utilizes a Gaussian Mixture Variational Graph Autoencoder (GMM-VGAE) to capture the diverse distribution of behavior policies from local observations. Extensive experiments across real-world urban traffic scenarios show that OffLight outperforms existing offline RL methods, achieving up to a 7.8% reduction in average travel time and 11.2% decrease in queue length. Ablation studies confirm the effectiveness of OffLight's components in handling heterogeneous data and improving policy performance. These results highlight OffLight's scalability and potential to improve urban traffic management without the risks of online learning.

Creating reinforcement learning agents that generalise effectively to new tasks is a key challenge in AI research. This paper introduces Fracture Cluster Options (FraCOs), a multi-level hierarchical reinforcement learning method that achieves state-of-the-art performance on difficult generalisation tasks. FraCOs identifies patterns in agent behaviour and forms options based on the expected future usefulness of those patterns, enabling rapid adaptation to new tasks. In tabular settings, FraCOs demonstrates effective transfer and improves performance as it grows in hierarchical depth. We evaluate FraCOs against state-of-the-art deep reinforcement learning algorithms in several complex procedurally generated environments. Our results show that FraCOs achieves higher in-distribution and out-of-distribution performance than competitors.

Recent advances in deep learning have shown significant potential for solving combinatorial optimization problems in real-time. Unlike traditional methods, deep learning can generate high-quality solutions efficiently, which is crucial for applications like routing and scheduling. However, existing approaches like deep reinforcement learning (RL) and behavioral cloning have notable limitations, with deep RL suffering from slow learning and behavioral cloning relying solely on expert actions, which can lead to generalization issues and neglect of the optimization objective. This paper introduces a novel offline RL method designed for combinatorial optimization problems with complex constraints, where the state is represented as a heterogeneous graph and the action space is variable. Our approach encodes actions in edge attributes and balances expected rewards with the imitation of expert solutions. We demonstrate the effectiveness of this method on job-shop scheduling and flexible job-shop scheduling benchmarks, achieving superior performance compared to state-of-the-art techniques.

Despite having powerful reasoning and inference capabilities, Large Language Models (LLMs) still need external tools to acquire real-time information retrieval or domain-specific expertise to solve complex tasks, which is referred to as tool learning. Existing tool learning methods primarily rely on tuning with expert trajectories, focusing on token-sequence learning from a linguistic perspective. However, there are several challenges: 1) imitating static trajectories limits their ability to generalize to new tasks. 2) even expert trajectories can be suboptimal, and better solution paths may exist. In this work, we introduce StepTool, a novel step-grained reinforcement learning framework to improve tool learning in LLMs. It consists of two components: Step-grained Reward Shaping, which assigns rewards at each tool interaction based on tool invocation success and its contribution to the task, and Step-grained Optimization, which uses policy gradient methods to optimize the model in a multi-step manner. Experimental results demonstrate that StepTool significantly outperforms existing methods in multi-step, tool-based tasks, providing a robust solution for complex task environments. Codes are available at https://github.com/yuyq18/StepTool.

Exploration remains a significant challenge in reinforcement learning, especially in environments where extrinsic rewards are sparse or non-existent. The recent rise of foundation models, such as CLIP, offers an opportunity to leverage pretrained, semantically rich embeddings that encapsulate broad and reusable knowledge. In this work we explore the potential of these foundation models not just to drive exploration, but also to analyze the critical role of the episodic novelty term in enhancing exploration effectiveness of the agent. We also investigate whether providing the intrinsic module with complete state information -- rather than just partial observations -- can improve exploration, despite the difficulties in handling small variations within large state spaces. Our experiments in the MiniGrid domain reveal that intrinsic modules can effectively utilize full state information, significantly increasing sample efficiency while learning an optimal policy. Moreover, we show that the embeddings provided by foundation models are sometimes even better than those constructed by the agent during training, further accelerating the learning process, especially when coupled with the episodic novelty term to enhance exploration.

Multi-Agent Reinforcement Learning (MARL) methods have shown promise in enabling agents to learn a shared communication protocol from scratch and accomplish challenging team tasks. However, the learned language is usually not interpretable to humans or other agents not co-trained together, limiting its applicability in ad-hoc teamwork scenarios. In this work, we propose a novel computational pipeline that aligns the communication space between MARL agents with an embedding space of human natural language by grounding agent communications on synthetic data generated by embodied Large Language Models (LLMs) in interactive teamwork scenarios. Our results demonstrate that introducing language grounding not only maintains task performance but also accelerates the emergence of communication. Furthermore, the learned communication protocols exhibit zero-shot generalization capabilities in ad-hoc teamwork scenarios with unseen teammates and novel task states. This work presents a significant step toward enabling effective communication and collaboration between artificial agents and humans in real-world teamwork settings.

Many critical treatment assignment problems are inherently dynamic in nature. For example, consider the allocation of job-training programs to newly unemployed individuals. Such programs are often funded through a fixed yearly budget determined in advance by the legislature, while job-seekers arrive at job centers sequentially throughout the year. Policymakers must decide whether to allocate training to each individual, recognizing that each decision affects the remaining budget and the availability of training for future applicants who may benefit even more. In essence, policymakers face a dynamic optimization problem, balancing immediate needs against long-term budgetary constraints.

Central to the development of universal learning systems is the ability to solve multiple tasks without retraining from scratch when new data arrives. This is crucial because each task requires significant training time. Addressing the problem of continual learning necessitates various methods due to the complexity of the problem space. This problem space includes: (1) addressing catastrophic forgetting to retain previously learned tasks, (2) demonstrating positive forward transfer for faster learning, (3) ensuring scalability across numerous tasks, and (4) facilitating learning without requiring task labels, even in the absence of clear task boundaries. In this paper, the Task-Agnostic Policy Distillation (TAPD) framework is introduced. This framework alleviates problems (1)-(4) by incorporating a task-agnostic phase, where an agent explores its environment without any external goal and maximizes only its intrinsic motivation. The knowledge gained during this phase is later distilled for further exploration. Therefore, the agent acts in a self-supervised manner by systematically seeking novel states. By utilizing task-agnostic distilled knowledge, the agent can solve downstream tasks more efficiently, leading to improved sample efficiency. Our code is available at the repository: https://github.com/wabbajack1/TAPD.

The multimedia content and streaming are a major means of information exchange in the modern era and there is an increasing demand for such services. This coupled with the advancement of future wireless networks B5G/6G and the proliferation of intelligent handheld mobile devices, has facilitated the availability of multimedia content to heterogeneous mobile users. Apart from the conventional video, the 360$^o$ videos have gained popularity with the emerging virtual reality applications. All formats of videos (conventional and 360$^o$) undergo processing, compression, and transmission across dynamic wireless channels with restricted bandwidth to facilitate the streaming services. This causes video impairments, leading to quality degradation and poses challenges in delivering good Quality-of-Experience (QoE) to the viewers. The QoE is a prominent subjective quality measure to assess multimedia services. This requires end-to-end QoE evaluation. Efficient multimedia streaming techniques can improve the service quality while dealing with dynamic network and end-user challenges. A paradigm shift in user-centric multimedia services is envisioned with a focus on Machine Learning (ML) based QoE modeling and streaming strategies. This survey paper presents a comprehensive overview of the overall and continuous, time varying QoE modeling for the purpose of QoE management in multimedia services. It also examines the recent research on intelligent and adaptive multimedia streaming strategies, with a special emphasis on ML based techniques for video (conventional and 360$^o$) streaming. This paper discusses the overall and continuous QoE modeling to optimize the end-user viewing experience, efficient video streaming with a focus on user-centric strategies, associated datasets for modeling and streaming, along with existing shortcoming and open challenges.

In the domain of continuous control, deep reinforcement learning (DRL) demonstrates promising results. However, the dependence of DRL on deep neural networks (DNNs) results in the demand for extensive data and increased computational complexity. To address this issue, a novel hybrid architecture for actor-critic reinforcement learning (RL) algorithms is introduced. The proposed architecture integrates the broad learning system (BLS) with DNN, aiming to merge the strengths of both distinct architectural paradigms. Specifically, the critic network is implemented using BLS, while the actor network is constructed with a DNN. For the estimations of the critic network parameters, ridge regression is employed, and the parameters of the actor network are optimized through gradient descent. The effectiveness of the proposed algorithm is evaluated by applying it to two classic continuous control tasks, and its performance is compared with the widely recognized deep deterministic policy gradient (DDPG) algorithm. Numerical results show that the proposed algorithm is superior to the DDPG algorithm in terms of computational efficiency, along with an accelerated learning trajectory. Application of the proposed algorithm in other actor-critic RL algorithms is suggested for investigation in future studies.