We study the common generalization of Markov decision processes (MDPs) with sets of transition probabilities, known as robust MDPs (RMDPs). A standard goal in RMDPs is to compute a policy that maximizes the expected return under an adversarial choice of the transition probabilities. If the uncertainty in the probabilities is independent between the states, known as s-rectangularity, such optimal robust policies can be computed efficiently using robust value iteration. However, there might still be multiple optimal robust policies, which, while equivalent with respect to the worst-case, reflect different expected returns under non-adversarial choices of the transition probabilities. Hence, we propose a refined policy selection criterion for RMDPs, drawing inspiration from the notions of dominance and best-effort in game theory. Instead of seeking a policy that only maximizes the worst-case expected return, we additionally require the policy to achieve a maximal expected return under different (i.e., not fully adversarial) transition probabilities. We call such a policy an optimal robust best-effort (ORBE) policy. We prove that ORBE policies always exist, characterize their structure, and present an algorithm to compute them with a manageable overhead over standard robust value iteration. ORBE policies offer a principled tie-breaker among optimal robust policies. Numerical experiments show the feasibility of our approach.

Automated Planning and Scheduling is among the growing areas in Artificial Intelligence (AI) where mention of LLMs has gained popularity. Based on a comprehensive review of 126 papers, this paper investigates eight categories based on the unique applications of LLMs in addressing various aspects of planning problems: language translation, plan generation, model construction, multi-agent planning, interactive planning, heuristics optimization, tool integration, and brain-inspired planning. For each category, we articulate the issues considered and existing gaps. A critical insight resulting from our review is that the true potential of LLMs unfolds when they are integrated with traditional symbolic planners, pointing towards a promising neuro-symbolic approach. This approach effectively combines the generative aspects of LLMs with the precision of classical planning methods. By synthesizing insights from existing literature, we underline the potential of this integration to address complex planning challenges. Our goal is to encourage the ICAPS community to recognize the complementary strengths of LLMs and symbolic planners, advocating for a direction in automated planning that leverages these synergistic capabilities to develop more advanced and intelligent planning systems. We aim to keep the categorization of papers updated on https://ai4society.github.io/LLM-Planning-Viz/, a collaborative resource that allows researchers to contribute and add new literature to the categorization.

This paper presents a novel semantics for the mA* epistemic action language that takes into consideration dynamic per-agent observability of events. Different from the original mA* semantics, the observability of events is defined locally at the level of possible worlds, giving a new method for compiling event models. Locally defined observability represents agents' uncertainty and false-beliefs about each others' ability to observe events. This allows for modeling second-order false-belief tasks where one agent does not know the truth about another agent's observations and resultant beliefs. The paper presents detailed constructions of event models for ontic, sensing, and truthful announcement action occurrences and proves various properties relating to agents' beliefs after the execution of an action. It also shows that the proposed approach can model second order false-belief tasks and satisfies the robustness and faithfulness criteria discussed by Bolander (2018, https://doi.org/10. 1007/978-3-319-62864-6_8).

Plansformer is a novel tool that utilizes a fine-tuned language model based on transformer architecture to generate symbolic plans. Transformers are a type of neural network architecture that have been shown to be highly effective in a range of natural language processing tasks. Unlike traditional planning systems that use heuristic-based search strategies, Plansformer is fine-tuned on specific classical planning domains to generate high-quality plans that are both fluent and feasible. Plansformer takes the domain and problem files as input (in PDDL) and outputs a sequence of actions that can be executed to solve the problem. We demonstrate the effectiveness of Plansformer on a variety of benchmark problems and provide both qualitative and quantitative results obtained during our evaluation, including its limitations. Plansformer has the potential to significantly improve the efficiency and effectiveness of planning in various domains, from logistics and scheduling to natural language processing and human-computer interaction. In addition, we provide public access to Plansformer via a website as well as an API endpoint; this enables other researchers to utilize our tool for planning and execution. The demo video is available at https://youtu.be/_1rlctCGsrk

Abstract The continuous interest in Artificial Intelligence (AI) has brought, among other things, the development of several scenarios where multiple artificial entities interact with each other. As for all the other autonomous settings, these multi-agent systems require orchestration. This is, generally, achieved through techniques derived from the vast field of Automated Planning. Notably, arbitration in multi-agent domains is not only tasked with regulating how the agents act, but must also consider the interactions between the agents’ information flows and must, therefore, reason on an epistemic level. This brings a substantial overhead that often diminishes the reasoning process’s usability in real-world situations. To address this problem, we present ECHO, a hierarchical framework that embeds classical and multi-agent epistemic (epistemic, for brevity) planners in a single architecture. The idea is to combine (i) classical; and(ii) epistemic solvers to model efficiently the agents’ interactions with the (i) ‘physical world’; and(ii) information flows, respectively. In particular, the presented architecture starts by planning on the ‘epistemic level’, with a high level of abstraction, focusing only on the information flows. Then it refines the planning process, due to the classical planner, to fully characterize the interactions with the ‘physical’ world. To further optimize the solving process, we introduced the concept of macros in epistemic planning and enriched the ‘classical’ part of the domain with goal-networks. Finally, we evaluated our approach in an actual robotic environment showing that our architecture indeed reduces the overall computational time.

Abstract Automated segmentation of computed tomography (CT) scans is the first step in the pipeline for the interpretation and identification of potential pathologies in human organs. Several methods based on machine learning (ML) are currently available, even if their precision is still outperformed by medical doctors. In this field there are some intrinsic limitations to ML approaches, such as the following: cost and time to acquire high-quality annotated scans for training; and a remarkable high variability of organ morphology due to age, conditions, genetics and acquisition. This paper outlines a new methodology based on Answer Set Programming, which returns reliable, easy-to-program and explainable interpretations. In particular, we focus on the CT scan analysis and retrieval of tree-like structure, corresponding to main blood vessels (arteries) arrangement. The structure is compared to the knowledge base of vessels contained in anatomy textbooks. The mapping of vessel names is computed by an Answer Set Programming program. This preliminary step produces a robust input to a reasoner for the multi-organ labelling and localization problem.

This paper proposes a research direction to advance AI which draws inspiration from cognitive theories of human decision making. The premise is that if we gain insights about the causes of some human capabilities that are still lacking in AI (for instance, adaptability, generalizability, common sense, and causal reasoning), we may obtain similar capabilities in an AI system by embedding these causal components. We hope that the high-level description of our vision included in this paper, as well as the several research questions that we propose to consider, can stimulate the AI research community to define, try and evaluate new methodologies, frameworks, and evaluation metrics, in the spirit of achieving a better understanding of both human and machine intelligence.

Abstract Designing agents that reason and act upon the world has always been one of the main objectives of the Artificial Intelligence community. While for planning in “simple” domains the agents can solely rely on facts about the world, in several contexts,e.g., economy, security, justice and politics, the mere knowledge of the world could be insufficient to reach a desired goal. In these scenarios,epistemicreasoning,i.e., reasoning about agents’ beliefs about themselves and about other agents’ beliefs, is essential to design winning strategies. This paper addresses the problem of reasoning in multi-agent epistemic settings exploiting declarative programming techniques. In particular, the paper presents an actual implementation of a multi-shotAnswer Set Programming-based planner that can reason in multi-agent epistemic settings, called PLATO (ePistemic muLti-agentAnswer seTprogramming sOlver). The ASP paradigm enables a concise and elegant design of the planner, w.r.t. other imperative implementations, facilitating the development of formal verification of correctness. The paper shows how the planner, exploiting an ad-hoc epistemic state representation and the efficiency of ASP solvers, has competitive performance results on benchmarks collected from the literature.