Autonomous vehicles that operate in urban environments shall comply with existing rules and reason about the interactions with other decision-making agents. In this paper, we introduce a decentralized and communication-free interaction-aware motion planner and apply it to Autonomous Surface Vessels (ASVs) in urban canals. We build upon a sampling-based method, namely Model Predictive Path Integral control (MPPI), and employ it to, in each time instance, compute both a collision-free trajectory for the vehicle and a prediction of other agents' trajectories, thus modeling interactions. To improve the method's efficiency in multi-agent scenarios, we introduce a two-stage sample evaluation strategy and define an appropriate cost function to achieve rule compliance. We evaluate this decentralized approach in simulations with multiple vessels in real scenarios extracted from Amsterdam's canals, showing superior performance than a state-of-the-art trajectory optimization framework and robustness when encountering different types of agents.

Understanding agent behaviour in Multi-Agent Systems (MAS) is an important problem in domains such as autonomous driving, disaster response, and sports analytics. Existing MAS problems typically use uniform timesteps with observations for all agents. In this work, we analyse the problem of agent location imputation, specifically posed in environments with non-uniform timesteps and limited agent observability (~95% missing values). Our approach uses Long Short-Term Memory and Graph Neural Network components to learn temporal and inter-agent patterns to predict the location of all agents at every timestep. We apply this to the domain of football (soccer) by imputing the location of all players in a game from sparse event data (e.g., shots and passes). Our model estimates player locations to within ~6.9m; a ~62% reduction in error from the best performing baseline. This approach facilitates downstream analysis tasks such as player physical metrics, player coverage, and team pitch control. Existing solutions to these tasks often require optical tracking data, which is expensive to obtain and only available to elite clubs. By imputing player locations from easy to obtain event data, we increase the accessibility of downstream tasks.

Swarm robotics is a creative method of organizing multi-robot structures, consisting of many basic robots influenced by communal insects. The greatest astonishing attribute of swarm robots is their capacity to function together to accomplish a collective objective. This paper addresses the list of current surveys, problems and algorithms that were stimulated in the research of Coordinated Movement in Swarm robotics. Algorithms for swarm robotics movement are contrasted, considering the swarm micro-robots to accomplish aggregation, creation, and clamouring by contrasting the relative computational simulations between the algorithms and simulations used.

Safety is essential for deploying Deep Reinforcement Learning (DRL) algorithms in real-world scenarios. Recently, verification approaches have been proposed to allow quantifying the number of violations of a DRL policy over input-output relationships, called properties. However, such properties are hard-coded and require task-level knowledge, making their application intractable in challenging safety-critical tasks. To this end, we introduce the Collection and Refinement of Online Properties (CROP) framework to design properties at training time. CROP employs a cost signal to identify unsafe interactions and use them to shape safety properties. Hence, we propose a refinement strategy to combine properties that model similar unsafe interactions. Our evaluation compares the benefits of computing the number of violations using standard hard-coded properties and the ones generated with CROP. We evaluate our approach in several robotic mapless navigation tasks and demonstrate that the violation metric computed with CROP allows higher returns and lower violations over previous Safe DRL approaches.

The classic literature on two-sided matching [Gale and Shapley, 1962, Roth and Xing, 1997, Haeringer and Wooders, 2011, e.g.], encompassing applications including long-and short-term labor markets, dating and marriage, school choice, and more, has typically focused on situations where agents are aware of their own preferences. The problem of learning preferences while participating in a repeated matching market first started receiving attention in the AI literature in the work of Das and Kamenica [2005], and the general idea of two-sided matching under unknown preferences has since been studied in economics and operations research as well Lee and Schwarz [2009], Johari et al. [2022]. This area of research has received renewed attention in the last few years, along with novel theoretical insights into convergence properties of upper-confidence-bound style algorithms Liu et al. [2021], Kong et al. [2022], Zhang et al. [2022]. The two-sided matching problem involves agents on two sides of a market who have preferences for each other but cannot communicate explicitly. The goal is to create a matching process that ensures stability, where no pairs of agents would rather be matched with each other over their current match. Gale and Shapley [1962] famously demonstrated, constructively, the existence of such matchings. The Gale-Shapley algorithm is structured around one side of the market proposing and the other side choosing whether to accept proposals. This theory has been applied to various markets, like matching medical students to residencies Roth and Peranson [1999] and students to schools Abdulkadiroğlu et al. [2005], with the assumption that agents know their own preferences. There has also been considerable interest in the AI community on two-sided matching in the presence of various constraints, e.g.

Exploration of the physical environment is an indispensable precursor to data acquisition and enables knowledge generation via analytical or direct trialing. Artificial Intelligence lacks the exploratory capabilities of even the most underdeveloped organisms, hindering its autonomy and adaptability. Supported by cognitive psychology, this works links human behavior and artificial agents to endorse self-development. In accordance with reported data, paradigms of epistemic and achievement emotion are embedded to machine-learning methodology contingent on their impact when decision making. A study is subsequently designed to mirror previous human trials, which artificial agents are made to undergo repeatedly towards convergence. Results demonstrate causality, learned by the vast majority of agents, between their internal states and exploration to match those reported for human counterparts. The ramifications of these findings are pondered for both research into human cognition and betterment of artificial intelligence.

Knowledge and skills can transfer from human teachers to human students. However, such direct transfer is often not scalable for physical tasks, as they require one-to-one interaction, and human teachers are not available in sufficient numbers. Machine learning enables robots to become experts and play the role of teachers to help in this situation. In this work, we formalize cooperative robot teaching as a Markov game, consisting of four key elements: the target task, the student model, the teacher model, and the interactive teaching-learning process. Under a moderate assumption, the Markov game reduces to a partially observable Markov decision process, with an efficient approximate solution. We illustrate our approach on two cooperative tasks, one in a simulated video game and one with a real robot.

Consider a graph G with n nodes and m edges, which represents a social network, and assume that initially each node is blue or white. In each round, all nodes simultaneously update their color to the most frequent color in their neighborhood. This is called the Majority Model (MM) if a node keeps its color in case of a tie and the Random Majority Model (RMM) if it chooses blue with probability 1/2 and white otherwise. We prove that there are graphs for which RMM needs exponentially many rounds to reach a stable configuration in expectation, and such a configuration can have exponentially many states (i.e., colorings). This is in contrast to MM, which is known to always reach a stable configuration with one or two states in $O(m)$ rounds. For the special case of a cycle graph C_n, we prove the stronger and tight bounds of $\lceil n/2\rceil-1$ and $O(n^2)$ in MM and RMM, respectively. Furthermore, we show that the number of stable colorings in MM on C_n is equal to $\Theta(\Phi^n)$, where $\Phi = (1+\sqrt{5})/2$ is the golden ratio, while it is equal to 2 for RMM. We also study the minimum size of a winning set, which is a set of nodes whose agreement on a color in the initial coloring enforces the process to end in a coloring where all nodes share that color. We present tight bounds on the minimum size of a winning set for both MM and RMM. Furthermore, we analyze our models for a random initial coloring, where each node is colored blue independently with some probability $p$ and white otherwise. Using some martingale analysis and counting arguments, we prove that the expected final number of blue nodes is respectively equal to $(2p^2-p^3)n/(1-p+p^2)$ and pn in MM and RMM on a cycle graph C_n. Finally, we conduct some experiments which complement our theoretical findings and also lead to the proposal of some intriguing open problems and conjectures to be tackled in future work.

Imitation from observation (IfO) is a learning paradigm that consists of training autonomous agents in a Markov Decision Process (MDP) by observing expert demonstrations without access to its actions. These demonstrations could be sequences of environment states or raw visual observations of the environment. Recent work in IfO has focused on this problem in the case of observations of low-dimensional environment states, however, access to these highly-specific observations is unlikely in practice. In this paper, we adopt a challenging, but more realistic problem formulation, learning control policies that operate on a learned latent space with access only to visual demonstrations of an expert completing a task. We present BootIfOL, an IfO algorithm that aims to learn a reward function that takes an agent trajectory and compares it to an expert, providing rewards based on similarity to agent behavior and implicit goal. We consider this reward function to be a distance metric between trajectories of agent behavior and learn it via contrastive learning. The contrastive learning objective aims to closely represent expert trajectories and to distance them from non-expert trajectories. The set of non-expert trajectories used in contrastive learning is made progressively more complex by bootstrapping from roll-outs of the agent learned through RL using the current reward function. We evaluate our approach on a variety of control tasks showing that we can train effective policies using a limited number of demonstrative trajectories, greatly improving on prior approaches that consider raw observations.

Inspired by recent progress in multi-agent Reinforcement Learning (RL), in this work we examine the collective intelligent behaviour of theoretical universal agents by introducing a weighted mixture operation. Given a weighted set of agents, their weighted mixture is a new agent whose expected total reward in any environment is the corresponding weighted average of the original agents' expected total rewards in that environment. Thus, if RL agent intelligence is quantified in terms of performance across environments, the weighted mixture's intelligence is the weighted average of the original agents' intelligences. This operation enables various interesting new theorems that shed light on the geometry of RL agent intelligence, namely: results about symmetries, convex agent-sets, and local extrema. We also show that any RL agent intelligence measure based on average performance across environments, subject to certain weak technical conditions, is identical (up to a constant factor) to performance within a single environment dependent on said intelligence measure.