Wiki articles are created and maintained by a crowd of editors, producing a continuous stream of reviews. Reviews can take the form of additions, reverts, or both. This crowdsourcing model is exposed to manipulation since neither reviews nor editors are automatically screened and purged. To protect articles against vandalism or damage, the stream of reviews can be mined to classify reviews and profile editors in real-time. The goal of this work is to anticipate and explain which reviews to revert. This way, editors are informed why their edits will be reverted. The proposed method employs stream-based processing, updating the profiling and classification models on each incoming event. The profiling uses side and content-based features employing Natural Language Processing, and editor profiles are incrementally updated based on their reviews. Since the proposed method relies on self-explainable classification algorithms, it is possible to understand why a review has been classified as a revert or a non-revert. In addition, this work contributes an algorithm for generating synthetic data for class balancing, making the final classification fairer. The proposed online method was tested with a real data set from Wikivoyage, which was balanced through the aforementioned synthetic data generation. The results attained near-90 % values for all evaluation metrics (accuracy, precision, recall, and F-measure).

We consider the dynamics of $n$ points on a sphere in $\mathbb{R}^d$ ($d \geq 2$) which attract each other according to a function $\varphi$ of their inner products. When $\varphi$ is linear ($\varphi(t) = t$), the points converge to a common value (i.e., synchronize) in various connectivity scenarios: this is part of classical work on Kuramoto oscillator networks. When $\varphi$ is exponential ($\varphi(t) = e^{\beta t}$), these dynamics correspond to a limit of how idealized transformers process data, as described by Geshkovski et al. (2024). Accordingly, they ask whether synchronization occurs for exponential $\varphi$. In the context of consensus for multi-agent control, Markdahl et al. (2018) show that for $d \geq 3$ (spheres), if the interaction graph is connected and $\varphi$ is increasing and convex, then the system synchronizes. What is the situation on circles ($d=2$)? First, we show that $\varphi$ being increasing and convex is no longer sufficient. Then we identify a new condition (that the Taylor coefficients of $\varphi'$ are decreasing) under which we do have synchronization on the circle. In so doing, we provide some answers to the open problems posed by Geshkovski et al. (2024).

We show that multi-agent reinforcement learning (MARL) with full parameter sharing outperforms independent and partially shared architectures in the competitive perfect-information homogenous game of Chinese Checkers. To run our experiments, we develop a new MARL environment: variable-size, six-player Chinese Checkers. This custom environment was developed in PettingZoo and supports all traditional rules of the game including chaining jumps. This is, to the best of our knowledge, the first implementation of Chinese Checkers that remains faithful to the true game. Chinese Checkers is difficult to learn due to its large branching factor and potentially infinite horizons. We borrow the concept of branching actions (submoves) from complex action spaces in other RL domains, where a submove may not end a player's turn immediately. This drastically reduces the dimensionality of the action space. Our observation space is inspired by AlphaGo with many binary game boards stacked in a 3D array to encode information. The PettingZoo environment, training and evaluation logic, and analysis scripts can be found on \href{https://github.com/noahadhikari/pettingzoo-chinese-checkers}{Github}.

Swarm robots, inspired by the emergence of animal herds, are robots that assemble a large number of modules and self-organize themselves to form specific morphologies and exhibit specific functions. These modular robots perform relatively simple actions and controls, and create macroscopic morphologies and functions through the interaction of a large number of modular robots. This research focuses on such self-organizing robots or swarm robots. The proposed algorithm is a model that applies the Turing pattern, one of the self-organization models, to make a group of modules accumulate and stay within a certain region. The proposed method utilizes the area within the spots of the Turing pattern as the aggregation region of the modules. Furthermore, it considers the value corresponding to the concentration distribution within the spotted pattern of the Turing pattern model (referred to as the potential value in this research), identifies the center of the region (spotted pattern), and makes it the center of the module group. By controlling the modules in the direction of the higher potential value, it succeeds in maintaining the shape of the module group as a whole while moving. The algorithm was validated using a two-dimensional simulation model. The unit module robot was assumed to have the following properties: 1) limited self-drive, 2) no module identifier, 3) information exchange only with adjacent modules, 4) no coordinate system, and 5) only simple arithmetic and memory functions. Using these modules, the devised algorithm was able to achieve not only the creation of static forms but also the realization of the following movements: 1) modules accumulate and grow, 2) modules move to the light source, 3) exit the gap while maintaining its shape, and 4) self-replication.

Recent work on dialogue-based collaborative plan acquisition (CPA) has suggested that Theory of Mind (ToM) modelling can improve missing knowledge prediction in settings with asymmetric skill-sets and knowledge. Although ToM was claimed to be important for effective collaboration, its real impact on this novel task remains under-explored. By representing plans as graphs and by exploiting task-specific constraints we show that, as performance on CPA nearly doubles when predicting one's own missing knowledge, the improvements due to ToM modelling diminish. This phenomenon persists even when evaluating existing baseline methods. To better understand the relevance of ToM for CPA, we report a principled performance comparison of models with and without ToM features. Results across different models and ablations consistently suggest that learned ToM features are indeed more likely to reflect latent patterns in the data with no perceivable link to ToM. This finding calls for a deeper understanding of the role of ToM in CPA and beyond, as well as new methods for modelling and evaluating mental states in computational collaborative agents.

Motivated by understanding the behavior of the Alternating Mirror Descent (AMD) algorithm for bilinear zero-sum games, we study the discretization of continuous-time Hamiltonian flow via the symplectic Euler method. We provide a framework for analysis using results from Hamiltonian dynamics, Lie algebra, and symplectic numerical integrators, with an emphasis on the existence and properties of a conserved quantity, the modified Hamiltonian (MH), for the symplectic Euler method. We compute the MH in closed-form when the original Hamiltonian is a quadratic function, and show that it generally differs from the other conserved quantity known previously in that case. We derive new error bounds on the MH when truncated at orders in the stepsize in terms of the number of iterations, $K$, and use these bounds to show an improved $\mathcal{O}(K^{1/5})$ total regret bound and an $\mathcal{O}(K^{-4/5})$ duality gap of the average iterates for AMD. Finally, we propose a conjecture which, if true, would imply that the total regret for AMD scales as $\mathcal{O}\left(K^{\varepsilon}\right)$ and the duality gap of the average iterates as $\mathcal{O}\left(K^{-1+\varepsilon}\right)$ for any $\varepsilon>0$, and we can take $\varepsilon=0$ upon certain convergence conditions for the MH.

Ensuring safety in MARL, particularly when deploying it in real-world applications such as autonomous driving, emerges as a critical challenge. To address this challenge, traditional safe MARL methods extend MARL approaches to incorporate safety considerations, aiming to minimize safety risk values. However, these safe MARL algorithms often fail to model other agents and lack convergence guarantees, particularly in dynamically complex environments. In this study, we propose a safe MARL method grounded in a Stackelberg model with bi-level optimization, for which convergence analysis is provided. Derived from our theoretical analysis, we develop two practical algorithms, namely Constrained Stackelberg Q-learning (CSQ) and Constrained Stackelberg Multi-Agent Deep Deterministic Policy Gradient (CS-MADDPG), designed to facilitate MARL decision-making in autonomous driving applications. To evaluate the effectiveness of our algorithms, we developed a safe MARL autonomous driving benchmark and conducted experiments on challenging autonomous driving scenarios, such as merges, roundabouts, intersections, and racetracks. The experimental results indicate that our algorithms, CSQ and CS-MADDPG, outperform several strong MARL baselines, such as Bi-AC, MACPO, and MAPPO-L, regarding reward and safety performance. The demos and source code are available at {https://github.com/SafeRL-Lab/Safe-MARL-in-Autonomous-Driving.git}.

Modern Tabletop Games present various interesting challenges for Multi-agent Reinforcement Learning. In this paper, we introduce PyTAG, a new framework that supports interacting with a large collection of games implemented in the Tabletop Games framework. In this work we highlight the challenges tabletop games provide, from a game-playing agent perspective, along with the opportunities they provide for future research. Additionally, we highlight the technical challenges that involve training Reinforcement Learning agents on these games. To explore the Multi-agent setting provided by PyTAG we train the popular Proximal Policy Optimisation Reinforcement Learning algorithm using self-play on a subset of games and evaluate the trained policies against some simple agents and Monte-Carlo Tree Search implemented in the Tabletop Games framework.

In multi-agent reinforcement learning (MARL), effective exploration is critical, especially in sparse reward environments. Although introducing global intrinsic rewards can foster exploration in such settings, it often complicates credit assignment among agents. To address this difficulty, we propose Individual Contributions as intrinsic Exploration Scaffolds (ICES), a novel approach to motivate exploration by assessing each agent's contribution from a global view. In particular, ICES constructs exploration scaffolds with Bayesian surprise, leveraging global transition information during centralized training. These scaffolds, used only in training, help to guide individual agents towards actions that significantly impact the global latent state transitions. Additionally, ICES separates exploration policies from exploitation policies, enabling the former to utilize privileged global information during training. Extensive experiments on cooperative benchmark tasks with sparse rewards, including Google Research Football (GRF) and StarCraft Multi-agent Challenge (SMAC), demonstrate that ICES exhibits superior exploration capabilities compared with baselines. The code is publicly available at https://github.com/LXXXXR/ICES.

Federated Reinforcement Learning (FRL) has been deemed as a promising solution for intelligent decision-making in the era of Artificial Internet of Things. However, existing FRL approaches often entail repeated interactions with the environment during local updating, which can be prohibitively expensive or even infeasible in many real-world domains. To overcome this challenge, this paper proposes a novel offline federated policy optimization algorithm, named $\texttt{DRPO}$, which enables distributed agents to collaboratively learn a decision policy only from private and static data without further environmental interactions. $\texttt{DRPO}$ leverages dual regularization, incorporating both the local behavioral policy and the global aggregated policy, to judiciously cope with the intrinsic two-tier distributional shifts in offline FRL. Theoretical analysis characterizes the impact of the dual regularization on performance, demonstrating that by achieving the right balance thereof, $\texttt{DRPO}$ can effectively counteract distributional shifts and ensure strict policy improvement in each federative learning round. Extensive experiments validate the significant performance gains of $\texttt{DRPO}$ over baseline methods.