Learning from demonstrations (LfD) has successfully trained robots to exhibit remarkable generalization capabilities. However, many powerful imitation techniques do not prioritize the feasibility of the robot behaviors they generate. In this work, we explore the feasibility of plans produced by LfD. As in prior work, we employ a temporal diffusion model with fixed start and goal states to facilitate imitation through in-painting. Unlike previous studies, we apply cold diffusion to ensure the optimization process is directed through the agent's replay buffer of previously visited states. This routing approach increases the likelihood that the final trajectories will predominantly occupy the feasible region of the robot's state space. We test this method in simulated robotic environments with obstacles and observe a significant improvement in the agent's ability to avoid these obstacles during planning.

While Large Language Models (LLMs) have demonstrated impressive accomplishments in both reasoning and planning, their abilities in multi-agent collaborations remains largely unexplored. This study evaluates LLM-based agents in a multi-agent cooperative text game with Theory of Mind (ToM) inference tasks, comparing their performance with Multi-Agent Reinforcement Learning (MARL) and planning-based baselines. We observed evidence of emergent collaborative behaviors and high-order Theory of Mind capabilities among LLM-based agents. Our results reveal limitations in LLM-based agents' planning optimization due to systematic failures in managing long-horizon contexts and hallucination about the task state. We explore the use of explicit belief state representations to mitigate these issues, finding that it enhances task performance and the accuracy of ToM inferences for LLM-based agents.

The graph identification problem consists of discovering the interactions among nodes in a network given their state/feature trajectories. This problem is challenging because the behavior of a node is coupled to all the other nodes by the unknown interaction model. Besides, high-dimensional and nonlinear state trajectories make it difficult to identify if two nodes are connected. Current solutions rely on prior knowledge of the graph topology and the dynamic behavior of the nodes, and hence, have poor generalization to other network configurations. To address these issues, we propose a novel learning-based approach that combines (i) a strongly convex program that efficiently uncovers graph topologies with global convergence guarantees and (ii) a self-attention encoder that learns to embed the original state trajectories into a feature space and predicts appropriate regularizers for the optimization program. In contrast to other works, our approach can identify the graph topology of unseen networks with new configurations in terms of number of nodes, connectivity or state trajectories. We demonstrate the effectiveness of our approach in identifying graphs in multi-robot formation and flocking tasks.

Multi-Agent Reinforcement Learning (MARL) has enjoyed significant recent progress thanks, in part, to the integration of deep learning techniques for modeling interactions in complex environments. This is naturally starting to benefit multi-robot systems (MRS) in the form of multi-robot RL (MRRL). However, existing infrastructure to train and evaluate policies predominantly focus on the challenges of coordinating virtual agents, and ignore characteristics important to robotic systems. Few platforms support realistic robot dynamics, and fewer still can evaluate Sim2Real performance of learned behavior. To address these issues, we contribute MARBLER: Multi-Agent RL Benchmark and Learning Environment for the Robotarium. MARBLER offers a robust and comprehensive evaluation platform for MRRL by marrying Georgia Tech's Robotarium (which enables rapid deployment on physical MRS) and OpenAI's Gym interface (which facilitates standardized use of modern learning algorithms). MARBLER offers a highly controllable environment with realistic dynamics, including barrier certificate-based obstacle avoidance. It allows anyone across the world to train and deploy MRRL algorithms on a physical testbed with reproducibility. Further, we introduce five novel scenarios inspired by common challenges in MRS and provide support for new custom scenarios. Finally, we use MARBLER to evaluate popular MARL algorithms and provide insights into their suitability for MRRL. In summary, MARBLER can be a valuable tool to the MRS research community by facilitating comprehensive and standardized evaluation of learning algorithms on realistic simulations and physical hardware. Links to our open-source framework and videos of real-world experiments can be found at https://shubhlohiya.github.io/MARBLER/.

We study a new non-stochastic federated multi-armed bandit problem with multiple agents collaborating via a communication network. The losses of the arms are assigned by an oblivious adversary that specifies the loss of each arm not only for each time step but also for each agent, which we call ``doubly adversarial". In this setting, different agents may choose the same arm in the same time step but observe different feedback. The goal of each agent is to find a globally best arm in hindsight that has the lowest cumulative loss averaged over all agents, which necessities the communication among agents. We provide regret lower bounds for any federated bandit algorithm under different settings, when agents have access to full-information feedback, or the bandit feedback. For the bandit feedback setting, we propose a near-optimal federated bandit algorithm called FEDEXP3. Our algorithm gives a positive answer to an open question proposed in Cesa-Bianchi et al. (2016): FEDEXP3 can guarantee a sub-linear regret without exchanging sequences of selected arm identities or loss sequences among agents. We also provide numerical evaluations of our algorithm to validate our theoretical results and demonstrate its effectiveness on synthetic and real-world datasets

Coordinating multiple agents that can communicate with each other to make decisions under uncertainty is a classical problem and has many different applications in computer science (Lynch, 1996), game theory (Chakravarty et al., 2014) and machine learning (Lanctot et al., 2017). We consider the multi-agent version of a multi-armed bandit problem which is one of the most fundamental decision making problems under uncertainty. In this problem, a learning agent needs to consider the exploration-exploitation trade-off, i.e. balancing the exploration of various actions in order to learn how much rewarding they are and selecting high-rewarding actions. In the multi-agent version of this problem, multiple agents collaborate with each other trying to maximize their individual cumulative rewards, and the challenge is to design efficient cooperative algorithms under communication constraints. We consider the nonstochastic (adversarial) multi-armed bandit problem in a cooperative multi-agent setting, with K 2 arms and N 1 agents.

Product disassembly plays a crucial role in the recycling, remanufacturing, and reuse of end-of-use (EoU) products. However, the current manual disassembly process is inefficient due to the complexity and variation of EoU products. While fully automating disassembly is not economically viable given the intricate nature of the task, there is potential in using human-robot collaboration (HRC) to enhance disassembly operations. HRC combines the flexibility and problem-solving abilities of humans with the precise repetition and handling of unsafe tasks by robots. Nevertheless, numerous challenges persist in technology, human workers, and remanufacturing work, that require comprehensive multidisciplinary research to bridge critical gaps. These challenges have motivated the authors to provide a detailed discussion on the opportunities and obstacles associated with introducing HRC to disassembly. In this regard, the authors have conducted a thorough review of the recent progress in HRC disassembly and present the insights gained from this analysis from three distinct perspectives: technology, workers, and work.

The coordination of autonomous vehicles is an open field that is addressed by different researches comprising many different techniques. In this paper we focus on decentralized approaches able to provide adaptability to different infrastructural and traffic conditions. We formalize an Emergent Behavior Approach that, as per our knowledge, has never been performed for this purpose, and a Decentralized Auction approach. We compare them against existing centralized negotiation approaches based on auctions and we determine under which conditions each approach is preferable to the others.

This document presents adequate formal terminology for the mathematical specification of a subset of Agent Based Models (ABMs) in the field of Demography. The simulation of the targeted ABMs follows a fixedstep single-clocked pattern. The proposed terminology further improves the model understanding and can act as a stand-alone protocol for the specification and optionally the documentation of a significant set of (demographic) ABMs. Nevertheless, it is imaginable the this terminology can serve as an inspiring basis for further improvement to the largely-informal widely-used model documentation and communication O.D.D. protocol [Grimm and et al., 2020, Amouroux et al., 2010] to reduce many sources of ambiguity which hinder model replications by other modelers. A published demographic model documentation, largely simplified version of the Lone Parent Model [Gostoli and Silverman, 2020] is separately published in [Elsheikh, 2023c] as illustration for the formal terminology presented here. The model was implemented in the Julia language [Elsheikh, 2023b] based on the Agents.jl julia package [Datseris et al., 2022].

This documentation specifies a simplified non-calibrated demographic agent-based model of the UK, a largely simplified version of the Lone Parent Model presented in [Gostolil and Silverman 2020]. In the presented model, individuals of an initial population are subject to ageing, deaths, births, divorces and marriages throughout a simplified map of towns of the UK. The specification employs the formal terminology presented in [Elsheikh 2023a]. The main purpose of the model is to explore and exploit capabilities of the state-of-the-art Agents.jl Julia package [Datseris2022] in the context of demographic modeling applications. Implementation is provided via the Julia package MiniDemographicABM.jl [Elsheikh 2023b]. A specific simulation is progressed with a user-defined simulation fixed step size on a hourly, daily, weekly, monthly basis or even an arbitrary user-defined clock rate. The model can serve for comparative studies if implemented in other agent-based modelling frameworks and programming languages. Moreover, the model serves as a base implementation to be adjusted to realistic large-scale socio-economics, pandemics or immigration studies mainly within a demographic context.