The main approach to evaluating communication is by assessing how well it facilitates coordination. If two or more individuals can coordinate through communication, it is generally assumed that they understand one another. We investigate this assumption in a signaling game where individuals develop a new vocabulary of signals to coordinate successfully. In our game, the individuals do not have common observations besides the communication signal and outcome of the interaction, i.e. received reward. This setting is used as a proxy to study communication emergence in populations of agents that perceive their environment very differently, e.g. hybrid populations that include humans and artificial agents. Agents develop signals, use them, and refine interpretations while not observing how other agents are using them. While populations always converge to optimal levels of coordination, in some cases, interacting agents interpret and use signals differently, converging to what we call successful misunderstandings. However, agents of population that coordinate using misaligned interpretations, are unable to establish successful coordination with new interaction partners. Not leading to coordination failure immediately, successful misunderstandings are difficult to spot and repair. Having at least three agents that all interact with each other are the two minimum conditions to ensure the emergence of shared interpretations. Under these conditions, the agent population exhibits this emergent property of compensating for the lack of shared observations of signal use, ensuring the emergence of shared interpretations.

Humans quickly learn new concepts from a small number of examples. Replicating this capacity with Artificial Intelligence (AI) systems has proven to be challenging. When it comes to learning subjective tasks-where there is an evident scarcity of data-this capacity needs to be recreated. In this work, we propose an intuitive human-agent teaching architecture in which the human can teach an agent how to perform a task by providing demonstrations, i.e., examples. To have an intuitive interaction, we argue that the agent should be able to learn incrementally from a few single examples. To allow for this, our objective is to broaden the agent's task understanding using domain knowledge. Then, using a learning method to enable the agent to learn efficiently from a limited number of examples. Finally, to optimize how human can select the most representative and less redundant examples to provide the agent with. We apply our proposed method to the subjective task of ingredient substitution, where the agent needs to learn how to substitute ingredients in recipes based on human examples. We replicate human input using the Recipe1MSubs dataset. In our experiments, the agent achieves half its task performance after only 100 examples are provided, compared to the complete training set of 50k examples. We show that by providing examples in strategic order along with a learning method that leverages external symbolic knowledge, the agent can generalize more efficiently.

This paper presents a framework towards prompting multi-robot teams with high-level tasks using natural language expressions. Our objective is to use the reasoning capabilities demonstrated by recent language models in understanding and decomposing human expressions of intent, and repurpose these for multi-robot collaboration and decision-making. The key challenge is that an individual's behavior in a collective can be hard to specify and interpret, and must continuously adapt to actions from others. This necessitates a framework that possesses the representational capacity required by the logic and semantics of a task, and yet supports decentralized and interactive real-time operation. We solve this dilemma by recognizing that a task can be represented as a deterministic finite automaton (DFA), and that recurrent neural networks (RNNs) can encode numerous automata. This allows us to distill the logic and sequential decompositions of sub-tasks obtained from a language model into an RNN, and align its internal states with the semantics of a given task. By training a graph neural network (GNN) control policy that is conditioned on the hidden states of the RNN and the language embeddings, our method enables robots to execute task-relevant actions in a decentralized manner. We present evaluations of this single light-weight interpretable model on various simulated and real-world multi-robot tasks that require sequential and collaborative behavior by the team -- sites.google.com/view/prompting-teams.

Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function representing discounted return. In this paper, we examine the role of these policy gradient and actor-critic algorithms in partially-observable multiagent environments. We show several candidate policy update rules and relate them to a foundation of regret minimization and multiagent learning techniques for the one-shot and tabular cases, leading to previously unknown convergence guarantees. We apply our method to model-free multiagent reinforcement learning in adversarial sequential decision problems (zero-sum imperfect information games), using RL-style function approximation. We evaluate on commonly used benchmark Poker domains, showing performance against fixed policies and empirical convergence to approximate Nash equilibria in self-play with rates similar to or better than a baseline model-free algorithm for zero-sum games, without any domain-specific state space reductions.

In this paper, we present two effective policy learning algorithms for multi-agent online coordination(MA-OC) problem. The first one, \texttt{MA-SPL}, not only can achieve the optimal $(1-\frac{c}{e})$-approximation guarantee for the MA-OC problem with submodular objectives but also can handle the unexplored $α$-weakly DR-submodular and $(γ,β)$-weakly submodular scenarios, where $c$ is the curvature of the investigated submodular functions, $α$ denotes the diminishing-return(DR) ratio and the tuple $(γ,β)$ represents the submodularity ratios. Subsequently, in order to reduce the reliance on the unknown parameters $α,γ,β$ inherent in the \texttt{MA-SPL} algorithm, we further introduce the second online algorithm named \texttt{MA-MPL}. This \texttt{MA-MPL} algorithm is entirely \emph{parameter-free} and simultaneously can maintain the same approximation ratio as the first \texttt{MA-SPL} algorithm. The core of our \texttt{MA-SPL} and \texttt{MA-MPL} algorithms is a novel continuous-relaxation technique termed as \emph{policy-based continuous extension}. Compared with the well-established \emph{multi-linear extension}, a notable advantage of this new \emph{policy-based continuous extension} is its ability to provide a lossless rounding scheme for any set function, thereby enabling us to tackle the challenging weakly submodular objectives. Finally, extensive simulations are conducted to validate the effectiveness of our proposed algorithms.

Despite its recent successes, Deep Reinforcement Learning (DRL) is notoriously sample-inefficient. We argue that this inefficiency stems from the standard practice of optimizing policies directly in the high-dimensional and highly redundant parameter space $Θ$. This challenge is greatly compounded in multi-task settings. In this work, we develop a novel, unsupervised approach that compresses the policy parameter space $Θ$ into a low-dimensional latent space $\mathcal{Z}$. We train a generative model $g:\mathcal{Z}\toΘ$ by optimizing a behavioral reconstruction loss, which ensures that the latent space is organized by functional similarity rather than proximity in parameterization. We conjecture that the inherent dimensionality of this manifold is a function of the environment's complexity, rather than the size of the policy network. We validate our approach in continuous control domains, showing that the parameterization of standard policy networks can be compressed up to five orders of magnitude while retaining most of its expressivity. As a byproduct, we show that the learned manifold enables task-specific adaptation via Policy Gradient operating in the latent space $\mathcal{Z}$.

Hospital patient falls remain a critical and costly challenge worldwide. While conventional fall prevention systems typically rely on post-fall detection or reactive alerts, they also often suffer from high false positive rates and fail to address the underlying patient needs that lead to bed-exit attempts. This paper presents a novel system architecture that leverages the Internet of Robotic Things (IoRT) to orchestrate human-robot-robot interaction for proactive and personalized patient assistance. The system integrates a privacy-preserving thermal sensing model capable of real-time bed-exit prediction, with two coordinated robotic agents that respond dynamically based on predicted intent and patient input. This orchestrated response could not only reduce fall risk but also attend to the patient's underlying motivations for movement, such as thirst, discomfort, or the need for assistance, before a hazardous situation arises. Our contributions with this pilot study are three-fold: (1) a modular IoRT-based framework enabling distributed sensing, prediction, and multi-robot coordination; (2) a demonstration of low-resolution thermal sensing for accurate, privacy-preserving preemptive bed-exit detection; and (3) results from a user study and systematic error analysis that inform the design of situationally aware, multi-agent interactions in hospital settings. The findings highlight how interactive and connected robotic systems can move beyond passive monitoring to deliver timely, meaningful assistance, empowering safer, more responsive care environments.

In today's data-sensitive landscape, distributed learning emerges as a vital tool, not only fortifying privacy measures but also streamlining computational operations. This becomes especially crucial within fully decentralized infrastructures where local processing is imperative due to the absence of centralized aggregation. Here, we introduce DYNAWEIGHT, a novel framework to information aggregation in multi-agent networks. DYNAWEIGHT offers substantial acceleration in decentralized learning with minimal additional communication and memory overhead. Unlike traditional static weight assignments, such as Metropolis weights, DYNAWEIGHT dynamically allocates weights to neighboring servers based on their relative losses on local datasets. Consequently, it favors servers possessing diverse information, particularly in scenarios of substantial data heterogeneity. Our experiments on various datasets MNIST, CIFAR10, and CIFAR100 incorporating various server counts and graph topologies, demonstrate notable enhancements in training speeds. Notably, DYNAWEIGHT functions as an aggregation scheme compatible with any underlying server-level optimization algorithm, underscoring its versatility and potential for widespread integration.