Importance sampling-based estimators for off-policy evaluation (OPE) are valued for their simplicity, unbiasedness, and reliance on relatively few assumptions. However, the variance of these estimators is often high, especially when trajectories are of different lengths. In this work, we introduce Omitting-States-Irrelevant-to-Return Importance Sampling (OSIRIS), an estimator which reduces variance by strategically omitting likelihood ratios associated with certain states. We formalize the conditions under which OSIRIS is unbiased and has lower variance than ordinary importance sampling, and we demonstrate these properties empirically.

Learning communication via deep reinforcement learning (RL) or imitation learning (IL) has recently been shown to be an effective way to solve Multi-Agent Path Finding (MAPF). However, existing communication based MAPF solvers focus on broadcast communication, where an agent broadcasts its message to all other or predefined agents. It is not only impractical but also leads to redundant information that could even impair the multi-agent cooperation. A succinct communication scheme should learn which information is relevant and influential to each agent's decision making process. To address this problem, we consider a request-reply scenario and propose Decision Causal Communication (DCC), a simple yet efficient model to enable agents to select neighbors to conduct communication during both training and execution. Specifically, a neighbor is determined as relevant and influential only when the presence of this neighbor causes the decision adjustment on the central agent. This judgment is learned only based on agent's local observation and thus suitable for decentralized execution to handle large scale problems. Empirical evaluation in obstacle-rich environment indicates the high success rate with low communication overhead of our method.

The notion of bounded rationality originated from the insight that perfectly rational behavior cannot be realized by agents with limited cognitive or computational resources. Research on bounded rationality, mainly initiated by Herbert Simon, has a longstanding tradition in economics and the social sciences, but also plays a major role in modern AI and intelligent agent design. Taking actions under bounded resources requires an agent to reflect on how to use these resources in an optimal way - hence, to reason and make decisions on a meta-level. In this paper, we will look at automated machine learning (AutoML) and related problems from the perspective of bounded rationality, essentially viewing an AutoML tool as an agent that has to train a model on a given set of data, and the search for a good way of doing so (a suitable "ML pipeline") as deliberation on a meta-level.

We present in this work an approach to reduce the communication of information needed on a multi-agent learning system inspired by Event Triggered Control (ETC) techniques. We consider a baseline scenario of a distributed Q-learning problem on a Markov Decision Process (MDP). Following an event-based approach, N agents explore the MDP and communicate experiences to a central learner only when necessary, which performs updates of the actor Q functions. We analyse the convergence guarantees retained with respect to a regular Q-learning algorithm, and present experimental results showing that event-based communication results in a substantial reduction of data transmission rates in such distributed systems. Additionally, we discuss what effects (desired and undesired) these event-based approaches have on the learning processes studied, and how they can be applied to more complex multi-agent learning systems.

Emergency personnel respond to various situations ranging from fire, medical, hazardous materials, industrial accidents, to natural disasters. Situations such as natural disasters or terrorist acts require a multifaceted response of firefighters, paramedics, hazmat teams, and other agencies. Engineering AI systems that aid emergency personnel proves to be a difficult system engineering problem. Mission-critical "edge AI" situations require low-latency, reliable analytics. To further add complexity, a high degree of model accuracy is required when lives are at stake, creating a need for the deployment of highly accurate, however computationally intensive models to resource-constrained devices. To address all these issues, we propose an agent-based architecture for deployment of AI agents via 5G service-based architecture.

We consider an information elicitation game where the center needs the agent to self-report her actual usage of a service and charges her a payment accordingly. The center can only observe a partial signal, representing part of the agent's true consumption, that is generated randomly from a publicly known distribution. The agent can report any information, as long as it does not contradict the signal, and the center issues a payment based on the reported information. Such problems find application in prosumer pricing, tax filing, etc., when the agent's actual consumption of a service is masked from the center and verification of the submitted reports is impractical. The key difference between the current problem and classic information elicitation problems is that the agent gets to observe the full signal and act strategically, but the center can only see the partial signal. For this seemingly impossible problem, we propose a penalty mechanism that elicits truthful self-reports in a repeated game. In particular, besides charging the agent the reported value, the mechanism charges a penalty proportional to her inconsistent reports. We show how a combination of the penalty rate and the length of the game incentivizes the agent to be truthful for the entire game, a phenomenon we call "fear of tomorrow verification". We show how approximate results for arbitrary distributions can be obtained by analyzing Bernoulli distributions. We extend our mechanism to a multi-agent cost sharing setting and give equilibrium results.

The traveling salesman problem (TSP) is a challenging Instead of solving mTSP as a combinatorial optimization, NP-hard problem, where given a group of cities (i.e., nodes) we focus on solving it as a decentralized cooperation problem, of a given graph (often complete), an agent needs to find where agents each construct their own tour towards a complete tour of this graph, i.e., a closed path from a a common objective. To this end, we rely on a threefold given starting node that visits all other nodes exactly once approach: first, we formulate mTSP as a sequential decision with minimal path length. TSP can be further extended to making problem and introduce a decision time gap that allows multiple traveling salesman problem (mTSP), where multiple agents to make decisions asynchronously for enhanced agents collaborate with each other to visit all cities from a collaboration. Second, we propose an attention based neural common starting node. Compared to TSP, mTSP has more network to allow agents to make individual decisions according general real world applications such as last-mile delivery, to their own observations, which provides agents with the UAV patrolling and transportation planning [1]. As classical ability to implicitly predict other agents' future decisions, combinatorial optimization problems, TSP and mTSP are by modeling the dependencies of all the agents and cities. commonly solved using exact or heuristic algorithms. Exact Third, we train our model using multi-agent reinforcement algorithms can theoretically guarantee optimal solutions [1], learning with parameter sharing, which provides our model [2], but rely on centralized, exhaustive planning, and thus do with natural scalability with the number of agents. We note not scale well with the number of agents and cities. On the that these tools are more general than mTSP, and could other hand, heuristic algorithms [1], [3] only find suboptimal extend to other robotic problems that need to address agent solutions but are significantly faster than exact algorithms.

In a ride-hailing system, an optimal relocation of vacant vehicles can significantly reduce fleet idling time and balance the supply-demand distribution, enhancing system efficiency and promoting driver satisfaction and retention. Model-free deep reinforcement learning (DRL) has been shown to dynamically learn the relocating policy by actively interacting with the intrinsic dynamics in large-scale ride-hailing systems. However, the issues of sparse reward signals and unbalanced demand and supply distribution place critical barriers in developing effective DRL models. Conventional exploration strategy (e.g., the $\epsilon$-greedy) may barely work under such an environment because of dithering in low-demand regions distant from high-revenue regions. This study proposes the deep relocating option policy (DROP) that supervises vehicle agents to escape from oversupply areas and effectively relocate to potentially underserved areas. We propose to learn the Laplacian embedding of a time-expanded relocation graph, as an approximation representation of the system relocation policy. The embedding generates task-agnostic signals, which in combination with task-dependent signals, constitute the pseudo-reward function for generating DROPs. We present a hierarchical learning framework that trains a high-level relocation policy and a set of low-level DROPs. The effectiveness of our approach is demonstrated using a custom-built high-fidelity simulator with real-world trip record data. We report that DROP significantly improves baseline models with 15.7% more hourly revenue and can effectively resolve the dithering issue in low-demand areas.

This paper introduces tvopt, a Python framework for prototyping and benchmarking time-varying (or online) optimization algorithms. The paper first describes the theoretical approach that informed the development of tvopt. Then it discusses the different components of the framework and their use for modeling and solving time-varying optimization problems. In particular, tvopt provides functionalities for defining both centralized and distributed online problems, and a collection of built-in algorithms to solve them, for example gradient-based methods, ADMM and other splitting methods. Moreover, the framework implements prediction strategies to improve the accuracy of the online solvers. The paper then proposes some numerical results on a benchmark problem and discusses their implementation using tvopt. The code for tvopt is available at https://github.com/nicola-bastianello/tvopt.

Mean field control (MFC) is an effective way to mitigate the curse of dimensionality of cooperative multi-agent reinforcement learning (MARL) problems. This work considers a collection of $N_{\mathrm{pop}}$ heterogeneous agents that can be segregated into $K$ classes such that the $k$-th class contains $N_k$ homogeneous agents. We aim to prove approximation guarantees of the MARL problem for this heterogeneous system by its corresponding MFC problem. We consider three scenarios where the reward and transition dynamics of all agents are respectively taken to be functions of $(1)$ joint state and action distributions across all classes, $(2)$ individual distributions of each class, and $(3)$ marginal distributions of the entire population. We show that, in these cases, the $K$-class MARL problem can be approximated by MFC with errors given as $e_1=\mathcal{O}(\frac{\sqrt{|\mathcal{X}||\mathcal{U}|}}{N_{\mathrm{pop}}}\sum_{k}\sqrt{N_k})$, $e_2=\mathcal{O}(\sqrt{|\mathcal{X}||\mathcal{U}|}\sum_{k}\frac{1}{\sqrt{N_k}})$ and $e_3=\mathcal{O}\left(\sqrt{|\mathcal{X}||\mathcal{U}|}\left[\frac{A}{N_{\mathrm{pop}}}\sum_{k\in[K]}\sqrt{N_k}+\frac{B}{\sqrt{N_{\mathrm{pop}}}}\right]\right)$, respectively, where $A, B$ are some constants and $|\mathcal{X}|,|\mathcal{U}|$ are the sizes of state and action spaces of each agent. Finally, we design a Natural Policy Gradient (NPG) based algorithm that, in the three cases stated above, can converge to an optimal MARL policy within $\mathcal{O}(e_j)$ error with a sample complexity of $\mathcal{O}(e_j^{-3})$, $j\in\{1,2,3\}$, respectively.