Many decision-making problems feature multiple objectives. In such problems, it is not always possible to know the preferences of a decision-maker for different objectives. However, it is often possible to observe the behavior of decision-makers. In multi-objective decision-making, preference inference is the process of inferring the preferences of a decision-maker for different objectives. This research proposes a Dynamic Weight-based Preference Inference (DWPI) algorithm that can infer the preferences of agents acting in multi-objective decision-making problems, based on observed behavior trajectories in the environment. The proposed method is evaluated on three multi-objective Markov decision processes: Deep Sea Treasure, Traffic, and Item Gathering. The performance of the proposed DWPI approach is compared to two existing preference inference methods from the literature, and empirical results demonstrate significant improvements compared to the baseline algorithms, in terms of both time requirements and accuracy of the inferred preferences. The Dynamic Weight-based Preference Inference algorithm also maintains its performance when inferring preferences for sub-optimal behavior demonstrations. In addition to its impressive performance, the Dynamic Weight-based Preference Inference algorithm does not require any interactions during training with the agent whose preferences are inferred, all that is required is a trajectory of observed behavior.

We introduce a new problem formulation, Double-Deck Multi-Agent Pickup and Delivery (DD-MAPD), which models the multi-robot shelf rearrangement problem in automated warehouses. DD-MAPD extends both Multi-Agent Pickup and Delivery (MAPD) and Multi-Agent Path Finding (MAPF) by allowing agents to move beneath shelves or lift and deliver a shelf to an arbitrary location, thereby changing the warehouse layout. We show that solving DD-MAPD is NP-hard. To tackle DD-MAPD, we propose MAPF-DECOMP, an algorithmic framework that decomposes a DD-MAPD instance into a MAPF instance for coordinating shelf trajectories and a subsequent MAPD instance with task dependencies for computing paths for agents. We also present an optimization technique to improve the performance of MAPF-DECOMP and demonstrate how to make MAPF-DECOMP complete for well-formed DD-MAPD instances, a realistic subclass of DD-MAPD instances. Our experimental results demonstrate the efficiency and effectiveness of MAPF-DECOMP, with the ability to compute high-quality solutions for large-scale instances with over one thousand shelves and hundreds of agents in just minutes of runtime.

Many complex scenarios require the coordination of agents possessing unique points of view and distinct semantic commitments. In response, standpoint logic (SL) was introduced in the context of knowledge integration, allowing one to reason with diverse and potentially conflicting viewpoints by means of indexed modalities. Another multi-modal logic of import is linear temporal logic (LTL) - a formalism used to express temporal properties of systems and processes, having prominence in formal methods and fields related to artificial intelligence. In this paper, we present standpoint linear temporal logic (SLTL), a new logic that combines the temporal features of LTL with the multi-perspective modelling capacity of SL. We define the logic SLTL, its syntax, and its semantics, establish its decidability and complexity, and provide a terminating tableau calculus to automate SLTL reasoning. Conveniently, this offers a clear path to extend existing LTL reasoners with practical reasoning support for temporal reasoning in multi-perspective settings.

This work studies the problem of ad hoc teamwork in teams composed of agents with differing computational capabilities. We consider cooperative multi-player games in which each agent's policy is constrained by a private capability parameter, and agents with higher capabilities are able to simulate the behavior of agents with lower capabilities (but not vice-versa). To address this challenge, we propose an algorithm that maintains a belief over the other agents' capabilities and incorporates this belief into the planning process. Our primary innovation is a novel framework based on capability type structures, which ensures that the belief updates remain consistent and informative without constructing the infinite hierarchy of beliefs. We also extend our techniques to settings where the agents' observations are subject to noise. We provide examples of games in which deviations in capability between oblivious agents can lead to arbitrarily poor outcomes, and experimentally validate that our capability-aware algorithm avoids the anti-cooperative behavior of the naive approach in these toy settings as well as a more complex cooperative checkers environment.

Abstract: In applications that involve human-robot interaction (HRI), human-robot teaming (HRT), and cooperative human-machine systems, the inference of the human partner's intent is of critical importance. This paper presents a method for the inference of the human operator's navigational intent, in the context of mobile robots that provide full or partial (e.g., shared control) teleoperation. We propose the Machine Learning Operator Intent Inference (MLOII) method, which a) processes spatial data collected by the robot's sensors; b) utilizes a supervised machine learning algorithm to estimate the operator's most probable navigational goal online. The proposed method's ability to reliably and efficiently infer the intent of the human operator is experimentally evaluated in realistically simulated exploration and remote inspection scenarios. The results in terms of accuracy and uncertainty indicate that the proposed method is comparable to another state-of-the-art method found in the literature.

Artificial Intelligence (AI) is about making computers that do the sorts of things that minds can do, and as we progress towards this goal, we tend to increasingly delegate human tasks to machines. However, AI systems usually do these tasks with an unusual imbalance of insight and understanding: new, deeper insights are present, yet many important qualities that a human mind would have previously brought to the activity are utterly absent. Therefore, it is crucial to ask which features of minds have we replicated, which are missing, and if that matters. One core feature that humans bring to tasks, when dealing with the ambiguity, emergent knowledge, and social context presented by the world, is reflection. Yet this capability is utterly missing from current mainstream AI. In this paper we ask what reflective AI might look like. Then, drawing on notions of reflection in complex systems, cognitive science, and agents, we sketch an architecture for reflective AI agents, and highlight ways forward.

It is challenging to quantify numerical preferences for different objectives in a multi-objective decision-making problem. However, the demonstrations of a user are often accessible. We propose an algorithm to infer linear preference weights from either optimal or near-optimal demonstrations. The algorithm is evaluated in three environments with two baseline methods. Empirical results demonstrate significant improvements compared to the baseline algorithms, in terms of both time requirements and accuracy of the inferred preferences. In future work, we plan to evaluate the algorithm's effectiveness in a multi-agent system, where one of the agents is enabled to infer the preferences of an opponent using our preference inference algorithm.

Constrained multiagent reinforcement learning (C-MARL) is gaining importance as MARL algorithms find new applications in real-world systems ranging from energy systems to drone swarms. Most C-MARL algorithms use a primal-dual approach to enforce constraints through a penalty function added to the reward. In this paper, we study the structural effects of this penalty term on the MARL problem. First, we show that the standard practice of using the constraint function as the penalty leads to a weak notion of safety. However, by making simple modifications to the penalty term, we can enforce meaningful probabilistic (chance and conditional value at risk) constraints. Second, we quantify the effect of the penalty term on the value function, uncovering an improved value estimation procedure. We use these insights to propose a constrained multiagent advantage actor critic (C-MAA2C) algorithm. Simulations in a simple constrained multiagent environment affirm that our reinterpretation of the primal-dual method in terms of probabilistic constraints is effective, and that our proposed value estimate accelerates convergence to a safe joint policy.

We investigate whether Deep Reinforcement Learning (Deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be composed into complex behavioral strategies in dynamic environments. We used Deep RL to train a humanoid robot with 20 actuated joints to play a simplified one-versus-one (1v1) soccer game. We first trained individual skills in isolation and then composed those skills end-to-end in a self-play setting. The resulting policy exhibits robust and dynamic movement skills such as rapid fall recovery, walking, turning, kicking and more; and transitions between them in a smooth, stable, and efficient manner - well beyond what is intuitively expected from the robot. The agents also developed a basic strategic understanding of the game, and learned, for instance, to anticipate ball movements and to block opponent shots. The full range of behaviors emerged from a small set of simple rewards. Our agents were trained in simulation and transferred to real robots zero-shot. We found that a combination of sufficiently high-frequency control, targeted dynamics randomization, and perturbations during training in simulation enabled good-quality transfer, despite significant unmodeled effects and variations across robot instances. Although the robots are inherently fragile, minor hardware modifications together with basic regularization of the behavior during training led the robots to learn safe and effective movements while still performing in a dynamic and agile way. Indeed, even though the agents were optimized for scoring, in experiments they walked 156% faster, took 63% less time to get up, and kicked 24% faster than a scripted baseline, while efficiently combining the skills to achieve the longer term objectives. Examples of the emergent behaviors and full 1v1 matches are available on the supplementary website.

Wikipedia is one of the most successful collaborative projects in history. It is the largest encyclopedia ever created, with millions of users worldwide relying on it as the first source of information as well as for fact-checking and in-depth research. As Wikipedia relies solely on the efforts of its volunteer-editors, its success might be particularly affected by toxic speech. In this paper, we analyze all 57 million comments made on user talk pages of 8.5 million editors across the six most active language editions of Wikipedia to study the potential impact of toxicity on editors' behaviour. We find that toxic comments consistently reduce the activity of editors, leading to an estimated loss of 0.5-2 active days per user in the short term. This amounts to multiple human-years of lost productivity when considering the number of active contributors to Wikipedia. The effects of toxic comments are even greater in the long term, as they significantly increase the risk of editors leaving the project altogether. Using an agent-based model, we demonstrate that toxicity attacks on Wikipedia have the potential to impede the progress of the entire project. Our results underscore the importance of mitigating toxic speech on collaborative platforms such as Wikipedia to ensure their continued success.