We study the performance of the gradient play algorithm for stochastic games (SGs), where each agent tries to maximize its own total discounted reward by making decisions independently based on current state information which is shared between agents. Policies are directly parameterized by the probability of choosing a certain action at a given state. We show that Nash equilibria (NEs) and first-order stationary policies are equivalent in this setting, and give a local convergence rate around strict NEs. Further, for a subclass of SGs called Markov potential games (which includes the setting with identical rewards as an important special case), we design a sample-based reinforcement learning algorithm and give a non-asymptotic global convergence rate analysis for both exact gradient play and our sample-based learning algorithm. Our result shows that the number of iterations to reach an $\epsilon$-NE scales linearly, instead of exponentially, with the number of agents. Local geometry and local stability are also considered, where we prove that strict NEs are local maxima of the total potential function and fully-mixed NEs are saddle points.

Urban Air Mobility (UAM) represents a promising solution for future transportation. In this study, we introduce VertiSim, an advanced event-driven simulator developed to evaluate e-VTOL transportation networks. Uniquely, VertiSim simultaneously models passenger, aircraft, and energy flows, reflecting the interrelated complexities of UAM systems. We utilized VertiSim to assess 19 operational scenarios serving a daily demand for 2,834 passengers with varying fleet sizes and vertiport distances. The study aims to support stakeholders in making informed decisions about fleet size, network design, and infrastructure development by understanding tradeoffs in passenger delay time, operational costs, and fleet utilization. Our simulations, guided by a heuristic dispatch and charge policy, indicate that fleet size significantly influences passenger delay and energy consumption within UAM networks. We find that increasing the fleet size can reduce average passenger delays, but this comes at the cost of higher operational expenses due to an increase in the number of repositioning flights. Additionally, our analysis highlights how vertiport distances impact fleet utilization: longer distances result in reduced total idle time and increased cruise and charge times, leading to more efficient fleet utilization but also longer passenger delays. These findings are important for UAM network planning, especially in balancing fleet size with vertiport capacity and operational costs. Simulator demo is available at: https://tinyurl.com/vertisim-vis

Pretrained representations from large-scale vision models have boosted the performance of downstream embodied policy learning. We look to understand whether additional self-supervised pretraining on exploration trajectories can build on these general-purpose visual representations to better support embodied planning in realistic environments. We evaluated four common auxiliary losses in embodied AI, two hindsight-based losses, and a standard imitation learning loss, by pretraining the agent's visual compression module and state belief representations with each objective and using CLIP as a representative visual backbone. The learned representations are then frozen for downstream multi-step evaluation on two goal-directed tasks. Surprisingly, we find that imitation learning on these exploration trajectories out-performs all other auxiliary losses even despite the exploration trajectories being dissimilar from the downstream tasks. This suggests that imitation of exploration may be ''all you need'' for building powerful planning representations. Additionally, we find that popular auxiliary losses can benefit from simple modifications to improve their support for downstream planning ability.

We derive necessary and sufficient conditions for leader-follower multi-agent systems such that we can further apply prescribed performance control to achieve the desired formation while satisfying certain transient constraints. A leader-follower framework is considered in the sense that a group of agents with external inputs are selected as leaders in order to drive the group of followers in a way that the entire system can achieve target formation within certain prescribed performance transient bounds. We first derive necessary conditions on the leader-follower graph topology under which the target formation together with the prescribed performance guarantees can be fulfilled. Afterwards, the derived necessary conditions are extended to necessary and sufficient conditions for leader-follower formation control under transient constraints. Finally, the proposed results are illustrated with simulation examples.

We propose and deploy an approach to continually train an instruction-following agent from feedback provided by users during collaborative interactions. During interaction, human users instruct an agent using natural language, and provide realtime binary feedback as they observe the agent following their instructions. We design a contextual bandit learning approach, converting user feedback to immediate reward. We evaluate through thousands of human-agent interactions, demonstrating 15.4% absolute improvement in instruction execution accuracy over time. We also show our approach is robust to several design variations, and that the feedback signal is roughly equivalent to the learning signal of supervised demonstration data.

Point clouds have shown significant potential in various domains, including Simultaneous Localization and Mapping (SLAM). However, existing approaches either rely on dense point clouds to achieve high localization accuracy or use generalized descriptors to reduce map size. Unfortunately, these two aspects seem to conflict with each other. To address this limitation, we propose a unified architecture, DeepPointMap, achieving excellent preference on both aspects. We utilize neural network to extract highly representative and sparse neural descriptors from point clouds, enabling memory-efficient map representation and accurate multi-scale localization tasks (e.g., odometry and loop-closure). Moreover, we showcase the versatility of our framework by extending it to more challenging multi-agent collaborative SLAM. The promising results obtained in these scenarios further emphasize the effectiveness and potential of our approach.

Simulation is a powerful tool to easily generate annotated data, and a highly desirable feature, especially in those domains where learning models need large training datasets. Machine learning and deep learning solutions, have proven to be extremely data-hungry and sometimes, the available real-world data are not sufficient to effectively model the given task. Despite the initial skepticism of a portion of the scientific community, the potential of simulation has been largely confirmed in many application areas, and the recent developments in terms of rendering and virtualization engines, have shown a good ability also in representing complex scenes. This includes environmental factors, such as weather conditions and surface reflectance, as well as human-related events, like human actions and behaviors. We present a human crowd simulator, called UniCrowd, and its associated validation pipeline. We show how the simulator can generate annotated data, suitable for computer vision tasks, in particular for detection and segmentation, as well as the related applications, as crowd counting, human pose estimation, trajectory analysis and prediction, and anomaly detection.

Data markets facilitate decentralized data exchange for applications such as prediction, learning, or inference. The design of these markets is challenged by varying privacy preferences as well as data similarity among data owners. Related works have often overlooked how data similarity impacts pricing and data value through statistical information leakage. We demonstrate that data similarity and privacy preferences are integral to market design and propose a query-response protocol using local differential privacy for a two-party data acquisition mechanism. In our regression data market model, we analyze strategic interactions between privacy-aware owners and the learner as a Stackelberg game over the asked price and privacy factor. Finally, we numerically evaluate how data similarity affects market participation and traded data value. A. Context and Motivation In recent years, there has been a surge in Internet of Things (IoT) devices with sensing and computing capabilities, leading to an abundance of IoT data. Shashi Raj Pandey and Petar Popovski are with the Connectivity Section, Department of Electronic Systems, Aalborg University, Denmark. Pierre Pinson has primary affiliation with Dyson School of Design Engineering, Imperial College London, UK. He is also affiliated to the Technical University of Denmark, Department of Technology, Management and Economics, as well as with Halfspace This work was supported by the Villum Investigator Grant "WATER" from the Velux Foundation, Denmark.

We investigate the problem of decentralized multi-agent navigation tasks, where multiple agents need to reach initially unassigned targets in a limited time. Classical planning-based methods suffer from expensive computation overhead at each step and offer limited expressiveness for complex cooperation strategies. In contrast, reinforcement learning (RL) has recently become a popular paradigm for addressing this issue. However, RL struggles with low data efficiency and cooperation when directly exploring (nearly) optimal policies in the large search space, especially with an increased agent number (e.g., 10+ agents) or in complex environments (e.g., 3D simulators). In this paper, we propose Multi-Agent Scalable GNN-based P lanner (MASP), a goal-conditioned hierarchical planner for navigation tasks with a substantial number of agents. MASP adopts a hierarchical framework to divide a large search space into multiple smaller spaces, thereby reducing the space complexity and accelerating training convergence. We also leverage graph neural networks (GNN) to model the interaction between agents and goals, improving goal achievement. Besides, to enhance generalization capabilities in scenarios with unseen team sizes, we divide agents into multiple groups, each with a previously trained number of agents. The results demonstrate that MASP outperforms classical planning-based competitors and RL baselines, achieving a nearly 100% success rate with minimal training data in both multi-agent particle environments (MPE) with 50 agents and a quadrotor 3-dimensional environment (OmniDrones) with 20 agents. Furthermore, the learned policy showcases zero-shot generalization across unseen team sizes.

We study building embodied agents for open-ended creative tasks. While existing methods build instruction-following agents that can perform diverse open-ended tasks, none of them demonstrates creativity -- the ability to give novel and diverse task solutions implicit in the language instructions. This limitation comes from their inability to convert abstract language instructions into concrete task goals in the environment and perform long-horizon planning for such complicated goals. Given the observation that humans perform creative tasks with the help of imagination, we propose a class of solutions for creative agents, where the controller is enhanced with an imaginator that generates detailed imaginations of task outcomes conditioned on language instructions. We introduce several approaches to implementing the components of creative agents. We implement the imaginator with either a large language model for textual imagination or a diffusion model for visual imagination. The controller can either be a behavior-cloning policy learned from data or a pre-trained foundation model generating executable codes in the environment. We benchmark creative tasks with the challenging open-world game Minecraft, where the agents are asked to create diverse buildings given free-form language instructions. In addition, we propose novel evaluation metrics for open-ended creative tasks utilizing GPT-4V, which holds many advantages over existing metrics. We perform a detailed experimental analysis of creative agents, showing that creative agents are the first AI agents accomplishing diverse building creation in the survival mode of Minecraft. Our benchmark and models are open-source for future research on creative agents (https://github.com/PKU-RL/Creative-Agents).