Markov Decision Processes (MDPs) are a classical model for decision making in the presence of uncertainty. Often they are viewed as state transformers with planning objectives defined with respect to paths over MDP states. An increasingly popular alternative is to view them as distribution transformers, giving rise to a sequence of probability distributions over MDP states. For instance, reachability and safety properties in modeling robot swarms or chemical reaction networks are naturally defined in terms of probability distributions over states. Verifying such distributional properties is known to be hard and often beyond the reach of classical state-based verification techniques. In this work, we consider the problems of certified policy (i.e. controller) verification and synthesis in MDPs under distributional reach-avoidance specifications. By certified we mean that, along with a policy, we also aim to synthesize a (checkable) certificate ensuring that the MDP indeed satisfies the property. Thus, given the target set of distributions and an unsafe set of distributions over MDP states, our goal is to either synthesize a certificate for a given policy or synthesize a policy along with a certificate, proving that the target distribution can be reached while avoiding unsafe distributions. To solve this problem, we introduce the novel notion of distributional reach-avoid certificates and present automated procedures for (1) synthesizing a certificate for a given policy, and (2) synthesizing a policy together with the certificate, both providing formal guarantees on certificate correctness. Our experimental evaluation demonstrates the ability of our method to solve several non-trivial examples, including a multi-agent robot-swarm model, to synthesize certified policies and to certify existing policies.

We study problems of federated control in Markov Decision Processes. To solve an MDP with large state space, multiple learning agents are introduced to collaboratively learn its optimal policy without communication of locally collected experience. In our settings, these agents have limited capabilities, which means they are restricted within different regions of the overall state space during the training process. In face of the difference among restricted regions, we firstly introduce concepts of leakage probabilities to understand how such heterogeneity affects the learning process, and then propose a novel communication protocol that we call Federated-Q protocol (FedQ), which periodically aggregates agents' knowledge of their restricted regions and accordingly modifies their learning problems for further training. In terms of theoretical analysis, we justify the correctness of FedQ as a communication protocol, then give a general result on sample complexity of derived algorithms FedQ-X with the RL oracle , and finally conduct a thorough study on the sample complexity of FedQ-SynQ. Specifically, FedQ-X has been shown to enjoy linear speedup in terms of sample complexity when workload is uniformly distributed among agents. Moreover, we carry out experiments in various environments to justify the efficiency of our methods.

We study an online learning problem in general-sum Stackelberg games, where players act in a decentralized and strategic manner. We study two settings depending on the type of information for the follower: (1) the limited information setting where the follower only observes its own reward, and (2) the side information setting where the follower has extra side information about the leader's reward. We show that for the follower, myopically best responding to the leader's action is the best strategy for the limited information setting, but not necessarily so for the side information setting -- the follower can manipulate the leader's reward signals with strategic actions, and hence induce the leader's strategy to converge to an equilibrium that is better off for itself. Based on these insights, we study decentralized online learning for both players in the two settings. Our main contribution is to derive last-iterate convergence and sample complexity results in both settings. Notably, we design a new manipulation strategy for the follower in the latter setting, and show that it has an intrinsic advantage against the best response strategy. Our theories are also supported by empirical results.

This paper shows how to construct genre patterns, whose purpose is to guide interactive story composition in a way that enforces thematic consistency. To start the discussion we argue, based on previous seminal works, for the existence of five fundamental genres, namely comedy, romance - in the sense of epic plots, flourishing since the twelfth century -, tragedy, satire, and mystery. To construct the patterns, a simple two-phase process is employed: first retrieving examples that match our genre characterizations, and then applying a form of most specific generalization to the groups of examples in order to find their commonalities. In both phases, AI agents are instrumental, with our PatternTeller prototype being called to operate the story composition process, offering the opportunity to generate stories from a given premise of the user, to be developed under the guidance of the chosen pattern and trying to accommodate the user's suggestions along the composition stages.

We investigate non-collaborative dialogue agents, which are expected to engage in strategic conversations with diverse users, for securing a mutual agreement that leans favorably towards the system's objectives. This poses two main challenges for existing dialogue agents: 1) The inability to integrate user-specific characteristics into the strategic planning, and 2) The difficulty of training strategic planners that can be generalized to diverse users. To address these challenges, we propose Trip to enhance the capability in tailored strategic planning, incorporating a user-aware strategic planning module and a population-based training paradigm. Through experiments on benchmark non-collaborative dialogue tasks, we demonstrate the effectiveness of Trip in catering to diverse users.

This paper considers a Min-Max Multiple Traveling Salesman Problem (MTSP), where the goal is to find a set of tours, one for each agent, to collectively visit all the cities while minimizing the length of the longest tour. Though MTSP has been widely studied, obtaining near-optimal solutions for large-scale problems is still challenging due to its NP-hardness. Recent efforts in data-driven methods face challenges of the need for hard-to-obtain supervision and issues with high variance in gradient estimations, leading to slow convergence and highly suboptimal solutions. We address these issues by reformulating MTSP as a bilevel optimization problem, using the concept of imperative learning (IL). This involves introducing an allocation network that decomposes the MTSP into multiple single-agent traveling salesman problems (TSPs). The longest tour from these TSP solutions is then used to self-supervise the allocation network, resulting in a new self-supervised, bilevel, end-to-end learning framework, which we refer to as imperative MTSP (iMTSP). Additionally, to tackle the high-variance gradient issues during the optimization, we introduce a control variate-based gradient estimation algorithm. Our experiments showed that these innovative designs enable our gradient estimator to converge 20% faster than the advanced reinforcement learning baseline and find up to 80% shorter tour length compared with Google OR-Tools MTSP solver, especially in large-scale problems (e.g. 1000 cities and 15 agents).

The conversational recommendation system (CRS) has been criticized regarding its user experience in real-world scenarios, despite recent significant progress achieved in academia. Existing evaluation protocols for CRS may prioritize system-centric factors such as effectiveness and fluency in conversation while neglecting user-centric aspects. Thus, we propose a new and inclusive evaluation protocol, Concept, which integrates both system- and user-centric factors. We conceptualise three key characteristics in representing such factors and further divide them into six primary abilities. To implement Concept, we adopt a LLM-based user simulator and evaluator with scoring rubrics that are tailored for each primary ability. Our protocol, Concept, serves a dual purpose. First, it provides an overview of the pros and cons in current CRS models. Second, it pinpoints the problem of low usability in the "omnipotent" ChatGPT and offers a comprehensive reference guide for evaluating CRS, thereby setting the foundation for CRS improvement.

Abstract-- This paper introduces UniGen, a novel approach to generating new traffic scenarios for evaluating and improving autonomous driving software through simulation. By predicting the distributions of all these variables from a shared global scenario embedding, we ensure that the final generated scenario is fully conditioned on all available context in the existing scene. Our unified modeling approach, combined with autoregressive agent injection, conditions the placement and motion trajectory of every new agent on all existing agents and their trajectories, leading to realistic scenarios with low collision rates. Our experimental results show that UniGen outperforms prior state of the art on the Waymo Open Motion Dataset. I. INTRODUCTION Autonomous Vehicles (AVs) have the potential to revolutionize In most prior diverse real-world dataset of such events is difficult and methods, ϕ and ψ are disjoint and trained separately via two expensive, due to the extensive mileage required to encounter different training procedures.

In this paper, we introduce a new method for the task of interaction transfer. Given an example interaction between a source object and an agent, our method can automatically infer both surface and spatial relationships for the agent and target objects within the same category, yielding more accurate and valid transfers. Specifically, our method characterizes the example interaction using a combined spatial and surface representation. We correspond the agent points and object points related to the representation to the target object space using a learned spatial and surface correspondence field, which represents objects as deformed and rotated signed distance fields. With the corresponded points, an optimization is performed under the constraints of our spatial and surface interaction representation and additional regularization. Experiments conducted on human-chair and hand-mug interaction transfer tasks show that our approach can handle larger geometry and topology variations between source and target shapes, significantly outperforming state-of-the-art methods.

Accurate trajectory prediction is crucial for ensuring safe and efficient autonomous driving. However, most existing methods overlook complex interactions between traffic participants that often govern their future trajectories. In this paper, we propose SocialFormer, an agent interaction-aware trajectory prediction method that leverages the semantic relationship between the target vehicle and surrounding vehicles by making use of the road topology. We also introduce an edge-enhanced heterogeneous graph transformer (EHGT) as the aggregator in a graph neural network (GNN) to encode the semantic and spatial agent interaction information. Additionally, we introduce a temporal encoder based on gated recurrent units (GRU) to model the temporal social behavior of agent movements. Finally, we present an information fusion framework that integrates agent encoding, lane encoding, and agent interaction encoding for a holistic representation of the traffic scene. We evaluate SocialFormer for the trajectory prediction task on the popular nuScenes benchmark and achieve state-of-the-art performance.