Learning in zero-sum games studies a situation where multiple agents competitively learn their strategy. In such multi-agent learning, we often see that the strategies cycle around their optimum, i.e., Nash equilibrium. When a game periodically varies (called a ``periodic'' game), however, the Nash equilibrium moves generically. How learning dynamics behave in such periodic games is of interest but still unclear. Interestingly, we discover that the behavior is highly dependent on the relationship between the two speeds at which the game changes and at which players learn. We observe that when these two speeds synchronize, the learning dynamics diverge, and their time-average does not converge. Otherwise, the learning dynamics draw complicated cycles, but their time-average converges. Under some assumptions introduced for the dynamical systems analysis, we prove that this behavior occurs. Furthermore, our experiments observe this behavior even if removing these assumptions. This study discovers a novel phenomenon, i.e., synchronization, and gains insight widely applicable to learning in periodic games.

In this paper, we propose a new method Strategist that utilizes LLMs to acquire new skills for playing multi-agent games through a self-improvement process. Our method gathers quality feedback through self-play simulations with Monte Carlo tree search and LLM-based reflection, which can then be used to learn high-level strategic skills such as how to evaluate states that guide the low-level execution.We showcase how our method can be used in both action planning and dialogue generation in the context of games, achieving good performance on both tasks. Specifically, we demonstrate that our method can help train agents with better performance than both traditional reinforcement learning-based approaches and other LLM-based skill learning approaches in games including the Game of Pure Strategy (GOPS) and The Resistance: Avalon.

Scheduling in multi-channel wireless communication system presents formidable challenges in effectively allocating resources. To address these challenges, we investigate a multi-resource restless matching bandit (MR-RMB) model for heterogeneous resource systems with an objective of maximizing long-term discounted total rewards while respecting resource constraints. We have also generalized to applications beyond multi-channel wireless. We discuss the Max-Weight Index Matching algorithm, which optimizes resource allocation based on learned partial indexes. We have derived the policy gradient theorem for index learning. Our main contribution is the introduction of a new Deep Index Policy (DIP), an online learning algorithm tailored for MR-RMB. DIP learns the partial index by leveraging the policy gradient theorem for restless arms with convoluted and unknown transition kernels of heterogeneous resources. We demonstrate the utility of DIP by evaluating its performance for three different MR-RMB problems. Our simulation results show that DIP indeed learns the partial indexes efficiently.

Motion planning is a key aspect of robotics. A common approach to address motion planning problems is trajectory optimization. Trajectory optimization can represent the high-level behaviors of robots through mathematical formulations. However, current trajectory optimization approaches have two main challenges. Firstly, their solution heavily depends on the initial guess, and they are prone to get stuck in local minima. Secondly, they face scalability limitations by increasing the number of constraints. This thesis endeavors to tackle these challenges by introducing four innovative trajectory optimization algorithms to improve reliability, scalability, and computational efficiency. There are two novel aspects of the proposed algorithms. The first key innovation is remodeling the kinematic constraints and collision avoidance constraints. Another key innovation lies in the design of algorithms that effectively utilize parallel computation on GPU accelerators. By using reformulated constraints and leveraging the computational power of GPUs, the proposed algorithms of this thesis demonstrate significant improvements in efficiency and scalability compared to the existing methods. Parallelization enables faster computation times, allowing for real-time decision-making in dynamic environments. Moreover, the algorithms are designed to adapt to changes in the environment, ensuring robust performance. Extensive benchmarking for each proposed optimizer validates their efficacy. Overall, this thesis makes a significant contribution to the field of trajectory optimization algorithms. It introduces innovative solutions that specifically address the challenges faced by existing methods. The proposed algorithms pave the way for more efficient and robust motion planning solutions in robotics by leveraging parallel computation and specific mathematical structures.

Power-to-Hydrogen is crucial for the renewable energy transition, yet existing literature lacks business models for the significant excess heat it generates. This study addresses this by evaluating three models for selling electrolyzer-generated heat to district heating grids: constant, flexible, and renewable-source hydrogen production, with and without heat sales. Using agent-based modeling and multi-criteria decision-making methods (VIKOR, TOPSIS, PROMETHEE), it finds that selling excess heat can cut hydrogen production costs by 5.6%. The optimal model operates flexibly with electricity spot prices, includes heat sales, and maintains a hydrogen price of 3.3 EUR/kg. Environmentally, hydrogen production from grid electricity could emit up to 13,783.8 tons of CO2 over four years from 2023. The best economic and environmental model uses renewable sources and sells heat at 3.5 EUR/kg

We present Topology-Guided ORCA as an alternative simulator to replace ORCA for planning smooth multi-agent motions in environments with static obstacles. Despite the impressive performance in simulating multi-agent crowd motion in free space, ORCA encounters a significant challenge in navigating the agents with the presence of static obstacles. ORCA ignores static obstacles until an agent gets too close to an obstacle, and the agent will get stuck if the obstacle intercepts an agent's path toward the goal. To address this challenge, Topology-Guided ORCA constructs a graph to represent the topology of the traversable region of the environment. We use a path planner to plan a path of waypoints that connects each agent's start and goal positions. The waypoints are used as a sequence of goals to guide ORCA. The experiments of crowd simulation in constrained environments show that our method outperforms ORCA in terms of generating smooth and natural motions of multiple agents in constrained environments, which indicates great potential of Topology-Guided ORCA for serving as an effective simulator for training constrained social navigation policies.

A novel approach for achieving fast evasion in self-localized swarms of Unmanned Aerial Vehicles (UAVs) threatened by an intruding moving object is presented in this paper. Motivated by natural self-organizing systems, the presented approach of fast and collective evasion enables the UAV swarm to avoid dynamic objects (interferers) that are actively approaching the group. The main objective of the proposed technique is the fast and safe escape of the swarm from an interferer ~discovered in proximity. This method is inspired by the collective behavior of groups of certain animals, such as schools of fish or flocks of birds. These animals use the limited information of their sensing organs and decentralized control to achieve reliable and effective group motion. The system presented in this paper is intended to execute the safe coordination of UAV swarms with a large number of agents. Similar to natural swarms, this system propagates a fast shock of information about detected interferers throughout the group to achieve dynamic and collective evasion. The proposed system is fully decentralized using only onboard sensors to mutually localize swarm agents and interferers, similar to how animals accomplish this behavior. As a result, the communication structure between swarm agents is not overwhelmed by information about the state (position and velocity) of each individual and it is reliable to communication dropouts. The proposed system and theory were numerically evaluated and verified in real-world experiments.

With the emergence of large language models (LLMs), LLM-powered multi-agent systems (LLM-MA systems) have been proposed to tackle real-world tasks. However, their agents mostly follow predefined Standard Operating Procedures (SOPs) that remain unchanged across the whole interaction, lacking autonomy and scalability. Additionally, current solutions often overlook the necessity for effective agent cooperation. To address the above limitations, we propose MegaAgent, a practical framework designed for autonomous cooperation in large-scale LLM Agent systems. MegaAgent leverages the autonomy of agents to dynamically generate agents based on task requirements, incorporating features such as automatically dividing tasks, systematic planning and monitoring of agent activities, and managing concurrent operations. In addition, MegaAgent is designed with a hierarchical structure and employs system-level parallelism to enhance performance and boost communication. We demonstrate the effectiveness of MegaAgent through Gobang game development, showing that it outperforms popular LLM-MA systems; and national policy simulation, demonstrating its high autonomy and potential to rapidly scale up to 590 agents while ensuring effective cooperation among them. Our results indicate that MegaAgent is the first autonomous large-scale LLM-MA system with no pre-defined SOPs, high effectiveness and scalability, paving the way for further research in this field. Our code is at https://anonymous.4open.science/r/MegaAgent-81F3.

Motivated by distributed selection problems, we formulate a new variant of multi-player multi-armed bandit (MAB) model, which captures stochastic arrival of requests to each arm, as well as the policy of allocating requests to players. The challenge is how to design a distributed learning algorithm such that players select arms according to the optimal arm pulling profile (an arm pulling profile prescribes the number of players at each arm) without communicating to each other. We first design a greedy algorithm, which locates one of the optimal arm pulling profiles with a polynomial computational complexity. We also design an iterative distributed algorithm for players to commit to an optimal arm pulling profile with a constant number of rounds in expectation. We apply the explore then commit (ETC) framework to address the online setting when model parameters are unknown. We design an exploration strategy for players to estimate the optimal arm pulling profile. Since such estimates can be different across different players, it is challenging for players to commit. We then design an iterative distributed algorithm, which guarantees that players can arrive at a consensus on the optimal arm pulling profile in only M rounds. We conduct experiments to validate our algorithm.

Quantum Artificial Intelligence (QAI) is the intersection of quantum computing and AI, a technological synergy with expected significant benefits for both. In this paper, we provide a brief overview of what has been achieved in QAI so far and point to some open questions for future research. In particular, we summarize some major key findings on the feasability and the potential of using quantum computing for solving computationally hard problems in various subfields of AI, and vice versa, the leveraging of AI methods for building and operating quantum computing devices.