Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning

We introduce a real-time strategy game environment built on Generals.io, a game that hosts thousands of active players each week across multiple game formats. Our environment is fully compatible with Gymnasium and PettingZoo, capable of running thousands of frames per second on commodity hardware. Our reference agent -- trained with supervised pre-training and self-play -- hits the top 0.003\% of the 1v1 human leaderboard after just 36 hours on a single H100 GPU. To accelerate learning, we incorporate potential-based reward shaping and memory features. Our contributions -- a modular RTS benchmark and a competitive, state-of-the-art baseline agent -- provide an accessible yet challenging platform for advancing multi-agent reinforcement learning research.

Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs

Multi-task multi-agent reinforcement learning (MT-MARL) has recently gained attention for its potential to enhance MARL's adaptability across multiple tasks. However, it is challenging for existing multi-task learning methods to handle complex problems, as they are unable to handle unrelated tasks and possess limited knowledge transfer capabilities. In this paper, we propose a hierarchical approach that efficiently addresses these challenges. The high-level module utilizes a skill graph, while the low-level module employs a standard MARL algorithm. Our approach offers two contributions. First, we consider the MT-MARL problem in the context of unrelated tasks, expanding the scope of MTRL. Second, the skill graph is used as the upper layer of the standard hierarchical approach, with training independent of the lower layer, effectively handling unrelated tasks and enhancing knowledge transfer capabilities. Extensive experiments are conducted to validate these advantages and demonstrate that the proposed method outperforms the latest hierarchical MAPPO algorithms. Videos and code are available at https://github.com/WindyLab/MT-MARL-SG

Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning

Offline multi-task reinforcement learning aims to learn a unified policy capable of solving multiple tasks using only pre-collected task-mixed datasets, without requiring any online interaction with the environment. However, it faces significant challenges in effectively sharing knowledge across tasks. Inspired by the efficient knowledge abstraction observed in human learning, we propose Goal-Oriented Skill Abstraction (GO-Skill), a novel approach designed to extract and utilize reusable skills to enhance knowledge transfer and task performance. Our approach uncovers reusable skills through a goal-oriented skill extraction process and leverages vector quantization to construct a discrete skill library. To mitigate class imbalances between broadly applicable and task-specific skills, we introduce a skill enhancement phase to refine the extracted skills. Furthermore, we integrate these skills using hierarchical policy learning, enabling the construction of a high-level policy that dynamically orchestrates discrete skills to accomplish specific tasks. Extensive experiments on diverse robotic manipulation tasks within the MetaWorld benchmark demonstrate the effectiveness and versatility of GO-Skill.

Optimizing Cognitive Networks: Reinforcement Learning Meets Energy Harvesting Over Cascaded Channels

This paper presents a reinforcement learning (RL) based approach to improve the physical layer security (PLS) of an underlay cognitive radio network (CRN) over cascaded channels. These channels are utilized in highly mobile networks such as cognitive vehicular networks (CVN). In addition, an eavesdropper aims to intercept the communications between secondary users (SUs). The SU receiver has full-duplex and energy harvesting capabilities to generate jamming signals to confound the eavesdropper and enhance security. Moreover, the SU transmitter extracts energy from ambient radio frequency signals in order to power subsequent transmissions to its intended receiver. To optimize the privacy and reliability of the SUs in a CVN, a deep Q-network (DQN) strategy is utilized where multiple DQN agents are required such that an agent is assigned at each SU transmitter. The objective for the SUs is to determine the optimal transmission power and decide whether to collect energy or transmit messages during each time period in order to maximize their secrecy rate. Thereafter, we propose a DQN approach to maximize the throughput of the SUs while respecting the interference threshold acceptable at the receiver of the primary user. According to our findings, our strategy outperforms two other baseline strategies in terms of security and reliability.

Learning safe, constrained policies via imitation learning: Connection to Probabilistic Inference and a Naive Algorithm

This article introduces an imitation learning method for learning maximum entropy policies that comply with constraints demonstrated by expert trajectories executing a task. The formulation of the method takes advantage of results connecting performance to bounds for the KL-divergence between demonstrated and learned policies, and its objective is rigorously justified through a connection to a probabilistic inference framework for reinforcement learning, incorporating the reinforcement learning objective and the objective to abide by constraints in an entropy maximization setting. The proposed algorithm optimizes the learning objective with dual gradient descent, supporting effective and stable training. Experiments show that the proposed method can learn effective policy models for constraints-abiding behaviour, in settings with multiple constraints of different types, accommodating different modalities of demonstrated behaviour, and with abilities to generalize.

Designing Adaptive Algorithms Based on Reinforcement Learning for Dynamic Optimization of Sliding Window Size in Multi-Dimensional Data Streams

Multi-dimensional data streams, prevalent in applications like IoT, financial markets, and real-time analytics, pose significant challenges due to their high velocity, unbounded nature, and complex inter-dimensional dependencies. Sliding window techniques are critical for processing such streams, but fixed-size windows struggle to adapt to dynamic changes like concept drift or bursty patterns. This paper proposes a novel reinforcement learning (RL)-based approach to dynamically optimize sliding window sizes for multi-dimensional data streams. By formulating window size selection as an RL problem, we enable an agent to learn an adaptive policy based on stream characteristics, such as variance, correlations, and temporal trends. Our method, RL-Window, leverages a Dueling Deep Q-Network (DQN) with prioritized experience replay to handle non-stationarity and high-dimensionality. Evaluations on benchmark datasets (UCI HAR, PAMAP2, Yahoo! Finance Stream) demonstrate that RL-Window outperforms state-of-the-art methods like ADWIN and CNN-Adaptive in classification accuracy, drift robustness, and computational efficiency. Additional qualitative analyses, extended metrics (e.g., energy efficiency, latency), and a comprehensive dataset characterization further highlight its adaptability and stability, making it suitable for real-time applications.

Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning

Despite advances in reinforcement learning (RL)-based video reasoning with large language models (LLMs), data collection and finetuning remain significant challenges. These methods often rely on large-scale supervised fine-tuning (SFT) with extensive video data and long Chain-of-Thought (CoT) annotations, making them costly and hard to scale. To address this, we present Video-RTS, a new approach to improve video reasoning capability with drastically improved data efficiency by combining data-efficient RL with a video-adaptive test-time scaling (TTS) strategy. Based on observations about the data scaling of RL samples, we skip the resource-intensive SFT step and employ efficient pure-RL training with output-based rewards, requiring no additional annotations or extensive fine-tuning. Furthermore, to utilize computational resources more efficiently, we introduce a sparse-to-dense video TTS strategy that improves inference by iteratively adding frames based on output consistency. We validate our approach on multiple video reasoning benchmarks, showing that Video-RTS surpasses existing video reasoning models by an average of 2.4% in accuracy using only 3.6% training samples. For example, Video-RTS achieves a 4.2% improvement on Video-Holmes, a recent and challenging video reasoning benchmark, and a 2.6% improvement on MMVU. Notably, our pure RL training and adaptive video TTS offer complementary strengths, enabling Video-RTS's strong reasoning performance.

Federated Learning-based MARL for Strengthening Physical-Layer Security in B5G Networks

This paper explores the application of a federated learning-based multi-agent reinforcement learning (MARL) strategy to enhance physical-layer security (PLS) in a multi-cellular network within the context of beyond 5G networks. At each cell, a base station (BS) operates as a deep reinforcement learning (DRL) agent that interacts with the surrounding environment to maximize the secrecy rate of legitimate users in the presence of an eavesdropper. This eavesdropper attempts to intercept the confidential information shared between the BS and its authorized users. The DRL agents are deemed to be federated since they only share their network parameters with a central server and not the private data of their legitimate users. Two DRL approaches, deep Q-network (DQN) and Reinforce deep policy gradient (RDPG), are explored and compared. The results demonstrate that RDPG converges more rapidly than DQN. In addition, we demonstrate that the proposed method outperforms the distributed DRL approach. Furthermore, the outcomes illustrate the trade-off between security and complexity.

Learning controllable dynamics through informative exploration

Environments with controllable dynamics are usually understood in terms of explicit models. However, such models are not always available, but may sometimes be learned by exploring an environment. In this work, we investigate using an information measure called "predicted information gain" to determine the most informative regions of an environment to explore next. Applying methods from reinforcement learning allows good suboptimal exploring policies to be found, and leads to reliable estimates of the underlying controllable dynamics. This approach is demonstrated by comparing with several myopic exploration approaches.

Bounomodes: the grazing ox algorithm for exploration of clustered anomalies

A common class of algorithms for informative path planning (IPP) follows boustrophedon ("as the ox turns") patterns, which aim to achieve uniform area coverage. However, IPP is often applied in scenarios where anomalies, such as plant diseases, pollution, or hurricane damage, appear in clusters. In such cases, prioritizing the exploration of anomalous regions over uniform coverage is beneficial. This work introduces a class of algorithms referred to as bounom\=odes ("as the ox grazes"), which alternates between uniform boustrophedon sampling and targeted exploration of detected anomaly clusters. While uniform sampling can be designed using geometric principles, close exploration of clusters depends on the spatial distribution of anomalies and must be learned. In our implementation, the close exploration behavior is learned using deep reinforcement learning algorithms. Experimental evaluations demonstrate that the proposed approach outperforms several established baselines.