AAAI.2023 - Planning, Routing, and Scheduling

| Total: 26

#1 Robust Neuro-Symbolic Goal and Plan Recognition [PDF1] [Copy] [Kimi] [REL]

Authors: Leonardo Amado, Ramon Fraga Pereira, Felipe Meneguzzi

Goal Recognition is the task of discerning the intended goal of an agent given a sequence of observations, whereas Plan Recognition consists of identifying the plan to achieve such intended goal. Regardless of the underlying techniques, most recognition approaches are directly affected by the quality of the available observations. In this paper, we develop neuro-symbolic recognition approaches that can combine learning and planning techniques, compensating for noise and missing observations using prior data. We evaluate our approaches in standard human-designed planning domains as well as domain models automatically learned from real-world data. Empirical experimentation shows that our approaches reliably infer goals and compute correct plans in the experimental datasets. An ablation study shows that outperform approaches that rely exclusively on the domain model, or exclusively on machine learning in problems with both noisy observations and low observability.


#2 Heuristic Search for Multi-Objective Probabilistic Planning [PDF1] [Copy] [Kimi] [REL]

Authors: Dillon Z. Chen, Felipe Trevizan, Sylvie Thiébaux

Heuristic search is a powerful approach that has successfully been applied to a broad class of planning problems, including classical planning, multi-objective planning, and probabilistic planning modelled as a stochastic shortest path (SSP) problem. Here, we extend the reach of heuristic search to a more expressive class of problems, namely multi-objective stochastic shortest paths (MOSSPs), which require computing a coverage set of non-dominated policies. We design new heuristic search algorithms MOLAO* and MOLRTDP, which extend well-known SSP algorithms to the multi-objective case. We further construct a spectrum of domain-independent heuristic functions differing in their ability to take into account the stochastic and multi-objective features of the problem to guide the search. Our experiments demonstrate the benefits of these algorithms and the relative merits of the heuristics.


#3 Zero-Knowledge Proofs for Classical Planning Problems [PDF1] [Copy] [Kimi] [REL]

Authors: Augusto B. Corrêa, Clemens Büchner, Remo Christen

In classical planning, the aim is to find a sequence of deterministic actions leading from the initial to a goal state. In this work, we consider the scenario where a party who knows the solution to a planning task, called the prover, wants to convince a second party, the verifier, that it has the solution without revealing any information about the solution itself. This is relevant in domains where privacy is important, for example when plans contain sensitive information or when the solution should not be revealed upfront. We achieve this by introducing a zero-knowledge protocol for plan existence. By restricting ourselves to tasks with polynomially-bounded plan length, we are able to construct a protocol that can be run efficiently by both the prover and verifier. The resulting protocol does not rely on any reduction, has a constant number of rounds, and runs in time polynomial in the size of the task.


#4 Planning with Hidden Parameter Polynomial MDPs [PDF1] [Copy] [Kimi] [REL]

Authors: Clarissa Costen, Marc Rigter, Bruno Lacerda, Nick Hawes

For many applications of Markov Decision Processes (MDPs), the transition function cannot be specified exactly. Bayes-Adaptive MDPs (BAMDPs) extend MDPs to consider transition probabilities governed by latent parameters. To act optimally in BAMDPs, one must maintain a belief distribution over the latent parameters. Typically, this distribution is described by a set of sample (particle) MDPs, and associated weights which represent the likelihood of a sample MDP being the true underlying MDP. However, as the number of dimensions of the latent parameter space increases, the number of sample MDPs required to sufficiently represent the belief distribution grows exponentially. Thus, maintaining an accurate belief in the form of a set of sample MDPs over complex latent spaces is computationally intensive, which in turn affects the performance of planning for these models. In this paper, we propose an alternative approach for maintaining the belief over the latent parameters. We consider a class of BAMDPs where the transition probabilities can be expressed in closed form as a polynomial of the latent parameters, and outline a method to maintain a closed-form belief distribution for the latent parameters which results in an accurate belief representation. Furthermore, the closed-form representation does away with the need to tune the number of sample MDPs required to represent the belief. We evaluate two domains and empirically show that the polynomial, closed-form, belief representation results in better plans than a sampling-based belief representation.


#5 Privacy Attacks on Schedule-Driven Data [PDF1] [Copy] [Kimi] [REL]

Authors: Stephan A. Fahrenkrog-Petersen, Arik Senderovich, Alexandra Tichauer, Ali Kaan Tutak, J. Christopher Beck, Matthias Weidlich

Schedules define how resources process jobs in diverse domains, reaching from healthcare to transportation, and, therefore, denote a valuable starting point for analysis of the underlying system. However, publishing a schedule may disclose private information on the considered jobs. In this paper, we provide a first threat model for published schedules, thereby defining a completely new class of data privacy problems. We then propose distance-based measures to assess the privacy loss incurred by a published schedule, and show their theoretical properties for an uninformed adversary, which can be used as a benchmark for informed attacks. We show how an informed attack on a published schedule can be phrased as an inverse scheduling problem. We instantiate this idea by formulating the inverse of a well-studied single-machine scheduling problem, namely minimizing the total weighted completion times. An empirical evaluation for synthetic scheduling problems shows the effectiveness of informed privacy attacks and compares the results to theoretical bounds on uninformed attacks.


#6 Markov Decision Processes with Time-Varying Geometric Discounting [PDF1] [Copy] [Kimi] [REL]

Authors: Jiarui Gan, Annika Hennes, Rupak Majumdar, Debmalya Mandal, Goran Radanovic

Canonical models of Markov decision processes (MDPs) usually consider geometric discounting based on a constant discount factor. While this standard modeling approach has led to many elegant results, some recent studies indicate the necessity of modeling time-varying discounting in certain applications. This paper studies a model of infinite-horizon MDPs with time-varying discount factors. We take a game-theoretic perspective – whereby each time step is treated as an independent decision maker with their own (fixed) discount factor – and we study the subgame perfect equilibrium (SPE) of the resulting game as well as the related algorithmic problems. We present a constructive proof of the existence of an SPE and demonstrate the EXPTIME-hardness of computing an SPE. We also turn to the approximate notion of epsilon-SPE and show that an epsilon-SPE exists under milder assumptions. An algorithm is presented to compute an epsilon-SPE, of which an upper bound of the time complexity, as a function of the convergence property of the time-varying discount factor, is provided.


#7 Learning-Augmented Algorithms for Online TSP on the Line [PDF1] [Copy] [Kimi] [REL]

Authors: Themistoklis Gouleakis, Konstantinos Lakis, Golnoosh Shahkarami

We study the online Traveling Salesman Problem (TSP) on the line augmented with machine-learned predictions. In the classical problem, there is a stream of requests released over time along the real line. The goal is to minimize the makespan of the algorithm. We distinguish between the open variant and the closed one, in which we additionally require the algorithm to return to the origin after serving all requests. The state of the art is a 1.64-competitive algorithm and a 2.04-competitive algorithm for the closed and open variants, respectively. In both cases, a tight lower bound is known. In both variants, our primary prediction model involves predicted positions of the requests. We introduce algorithms that (i) obtain a tight 1.5 competitive ratio for the closed variant and a 1.66 competitive ratio for the open variant in the case of perfect predictions, (ii) are robust against unbounded prediction error, and (iii) are smooth, i.e., their performance degrades gracefully as the prediction error increases. Moreover, we further investigate the learning-augmented setting in the open variant by additionally considering a prediction for the last request served by the optimal offline algorithm. Our algorithm for this enhanced setting obtains a 1.33 competitive ratio with perfect predictions while also being smooth and robust, beating the lower bound of 1.44 we show for our original prediction setting for the open variant. Also, we provide a lower bound of 1.25 for this enhanced setting.


#8 Networked Restless Bandits with Positive Externalities [PDF1] [Copy] [Kimi] [REL]

Authors: Christine Herlihy, John P. Dickerson

Restless multi-armed bandits are often used to model budget-constrained resource allocation tasks where receipt of the resource is associated with an increased probability of a favorable state transition. Prior work assumes that individual arms only benefit if they receive the resource directly. However, many allocation tasks occur within communities and can be characterized by positive externalities that allow arms to derive partial benefit when their neighbor(s) receive the resource. We thus introduce networked restless bandits, a novel multi-armed bandit setting in which arms are both restless and embedded within a directed graph. We then present Greta, a graph-aware, Whittle index-based heuristic algorithm that can be used to efficiently construct a constrained reward-maximizing action vector at each timestep. Our empirical results demonstrate that Greta outperforms comparison policies across a range of hyperparameter values and graph topologies. Code and appendices are available at https://github.com/crherlihy/networked_restless_bandits.


#9 Planning for Learning Object Properties [PDF1] [Copy] [Kimi] [REL]

Authors: Leonardo Lamanna, Luciano Serafini, Mohamadreza Faridghasemnia, Alessandro Saffiotti, Alessandro Saetti, Alfonso Gerevini, Paolo Traverso

Autonomous agents embedded in a physical environment need the ability to recognize objects and their properties from sensory data. Such a perceptual ability is often implemented by supervised machine learning models, which are pre-trained using a set of labelled data. In real-world, open-ended deployments, however, it is unrealistic to assume to have a pre-trained model for all possible environments. Therefore, agents need to dynamically learn/adapt/extend their perceptual abilities online, in an autonomous way, by exploring and interacting with the environment where they operate. This paper describes a way to do so, by exploiting symbolic planning. Specifically, we formalize the problem of automatically training a neural network to recognize object properties as a symbolic planning problem (using PDDL). We use planning techniques to produce a strategy for automating the training dataset creation and the learning process. Finally, we provide an experimental evaluation in both a simulated and a real environment, which shows that the proposed approach is able to successfully learn how to recognize new object properties.


#10 Fully Online Matching with Stochastic Arrivals and Departures [PDF1] [Copy] [Kimi] [REL]

Authors: Zihao Li, Hao Wang, Zhenzhen Yan

We study a fully online matching problem with stochastic arrivals and departures. In this model, each online arrival follows a known identical and independent distribution over a fixed set of agent types. Its sojourn time is unknown in advance and follows type-specific distributions with known expectations. The goal is to maximize the weighted reward from successful matches. To solve this problem, we first propose a linear program (LP)-based algorithm whose competitive ratio is lower bounded by 0.155 under mild conditions. We further achieve better ratios in some special cases. To demonstrate the challenges of the problem, we further establish several hardness results. In particular, we show that no online algorithm can achieve a competitive ratio better than 2/3 in this model and there is no LP-based algorithm (with respect to our proposed LP) with a competitive ratio better than 1/3. Finally, we demonstrate the effectiveness and efficiency of our algorithm numerically.


#11 Towards Automated Modeling Assistance: An Efficient Approach for Repairing Flawed Planning Domains [PDF1] [Copy] [Kimi] [REL]

Authors: Songtuan Lin, Alban Grastien, Pascal Bercher

Designing a planning domain is a difficult task in AI planning. Assisting tools are thus required if we want planning to be used more broadly. In this paper, we are interested in automatically correcting a flawed domain. In particular, we are concerned with the scenario where a domain contradicts a plan that is known to be valid. Our goal is to repair the domain so as to turn the plan into a solution. Specifically, we consider both grounded and lifted representations support for negative preconditions and show how to explore the space of repairs to find the optimal one efficiently. As an evidence of the efficiency of our approach, the experiment results show that all flawed domains except one in the benchmark set can be repaired optimally by our approach within one second.


#12 Was Fixing This Really That Hard? On the Complexity of Correcting HTN Domains [PDF1] [Copy] [Kimi] [REL]

Authors: Songtuan Lin, Pascal Bercher

Automated modeling assistance is indispensable to the AI planning being deployed in practice, notably in industry and other non-academic contexts. Yet, little progress has been made that goes beyond smart interfaces like programming environments. They focus on autocompletion, but lack intelligent support for guiding the modeler. As a theoretical foundation of a first step towards this direction, we study the computational complexity of correcting a flawed Hierarchical Task Network (HTN) planning domain. Specifically, a modeler provides a (white) list of plans that are supposed to be solutions, and likewise a (black) list of plans that shall not be solutions. We investigate the complexity of finding a set of (optimal or suboptimal) model corrections so that those plans are (resp. not) solutions to the corrected model. More specifically, we factor out each hardness source that contributes towards NP-hardness, including one that we deem important for many other complexity investigations that go beyond our specific context of application. All complexities range between NP and Sigma-2-p, rising the hope for efficient practical tools in the future.


#13 On Total-Order HTN Plan Verification with Method Preconditions – An Extension of the CYK Parsing Algorithm [PDF1] [Copy] [Kimi] [REL]

Authors: Songtuan Lin, Gregor Behnke, Simona Ondrčková, Roman Barták, Pascal Bercher

In this paper, we consider the plan verification problem for totally ordered (TO) HTN planning. The problem is proved to be solvable in polynomial time by recognizing its connection to the membership decision problem for context-free grammars. Currently, most HTN plan verification approaches do not have special treatments for the TO configuration, and the only one features such an optimization still relies on an exhaustive search. Hence, we will develop a new TOHTN plan verification approach in this paper by extending the standard CYK parsing algorithm which acts as the best decision procedure in general.


#14 A Dynamics and Task Decoupled Reinforcement Learning Architecture for High-Efficiency Dynamic Target Intercept [PDF1] [Copy] [Kimi] [REL]

Authors: Dora D. Liu, Liang Hu, Qi Zhang, Tangwei Ye, Usman Naseem, Zhong Yuan Lai

Due to the flexibility and ease of control, unmanned aerial vehicles (UAVs) have been increasingly used in various scenarios and applications in recent years. Training UAVs with reinforcement learning (RL) for a specific task is often expensive in terms of time and computation. However, it is known that the main effort of the learning process is made to fit the low-level physical dynamics systems instead of the high-level task itself. In this paper, we study to apply UAVs in the dynamic target intercept (DTI) task, where the dynamics systems equipped by different UAV models are correspondingly distinct. To this end, we propose a dynamics and task decoupled RL architecture to address the inefficient learning procedure, where the RL module focuses on modeling the DTI task without involving physical dynamics, and the design of states, actions, and rewards are completely task-oriented while the dynamics control module can adaptively convert actions from the RL module to dynamics signals to control different UAVs without retraining the RL module. We show the efficiency and efficacy of our results in comparison and ablation experiments against state-of-the-art methods.


#15 AlphaRoute: Large-Scale Coordinated Route Planning via Monte Carlo Tree Search [PDF1] [Copy] [Kimi] [REL]

Authors: Guiyang Luo, Yantao Wang, Hui Zhang, Quan Yuan, Jinglin Li

This paper proposes AlphaRoute, an AlphaGo inspired algorithm for coordinating large-scale routes, built upon graph attention reinforcement learning and Monte Carlo Tree Search (MCTS). We first partition the road network into regions and model large-scale coordinated route planning as a Markov game, where each partitioned region is treated as a player instead of each driver. Then, AlphaRoute applies a bilevel optimization framework, consisting of several region planners and a global planner, where the region planner coordinates the route choices for vehicles located in the region and generates several strategies, and the global planner evaluates the combination of strategies. AlphaRoute is built on graph attention network for evaluating each state and MCTS algorithm for dynamically visiting and simulating the future state for narrowing down the search space. AlphaRoute is capable of 1) bridging user fairness and system efficiency, 2) achieving higher search efficiency by alleviating the curse of dimensionality problems, and 3) making an effective and informed route planning by simulating over the future to capture traffic dynamics. Comprehensive experiments are conducted on two real-world road networks as compared with several baselines to evaluate the performance, and results show that AlphaRoute achieves the lowest travel time, and is efficient and effective for coordinating large-scale routes and alleviating the traffic congestion problem. The code will be publicly available.


#16 Learning Rational Subgoals from Demonstrations and Instructions [PDF1] [Copy] [Kimi2] [REL]

Authors: Zhezheng Luo, Jiayuan Mao, Jiajun Wu, Tomás Lozano-Pérez, Joshua B. Tenenbaum, Leslie Pack Kaelbling

We present a framework for learning useful subgoals that support efficient long-term planning to achieve novel goals. At the core of our framework is a collection of rational subgoals (RSGs), which are essentially binary classifiers over the environmental states. RSGs can be learned from weakly-annotated data, in the form of unsegmented demonstration trajectories, paired with abstract task descriptions, which are composed of terms initially unknown to the agent (e.g., collect-wood then craft-boat then go-across-river). Our framework also discovers dependencies between RSGs, e.g., the task collect-wood is a helpful subgoal for the task craft-boat. Given a goal description, the learned subgoals and the derived dependencies facilitate off-the-shelf planning algorithms, such as A* and RRT, by setting helpful subgoals as waypoints to the planner, which significantly improves performance-time efficiency. Project page: https://rsg.csail.mit.edu


#17 Learning Safe Numeric Action Models [PDF1] [Copy] [Kimi] [REL]

Authors: Argaman Mordoch, Brendan Juba, Roni Stern

Powerful domain-independent planners have been developed to solve various types of planning problems. These planners often require a model of the acting agent's actions, given in some planning domain description language. Yet obtaining such an action model is a notoriously hard task. This task is even more challenging in mission-critical domains, where a trial-and-error approach to learning how to act is not an option. In such domains, the action model used to generate plans must be safe, in the sense that plans generated with it must be applicable and achieve their goals. Learning safe action models for planning has been recently explored for domains in which states are sufficiently described with Boolean variables. In this work, we go beyond this limitation and propose the NSAM algorithm. NSAM runs in time that is polynomial in the number of observations and, under certain conditions, is guaranteed to return safe action models. We analyze its worst-case sample complexity, which may be intractable for some domains. Empirically, however, NSAM can quickly learn a safe action model that can solve most problems in the domain.


#18 Automated Verification of Social Laws in Numeric Settings [PDF1] [Copy] [Kimi] [REL]

Authors: Ronen Nir, Alexander Shleyfman, Erez Karpas

It is possible for agents operating in a shared environment to interfere with one another. One mechanism of coordination is called Social Law. Enacting such a law in a multi-agent setting restricts agents' behaviors. Robustness, in this case, ensures that the agents do not harmfully interfere with each other and that each agent achieves its goals regardless of what other agents do. Previous work on social law verification examined only the case of boolean state variables. However, many real-world problems require reasoning with numeric variables. Moreover, numeric fluents allow a more compact representation of multiple planning problems. In this paper, we develop a method to verify whether a given social law is robust via compilation to numeric planning. A solution to this compilation constitutes a counterexample to the robustness of the problem, i.e., evidence of cross-agent conflict. Thus, the social law is robust if and only if the proposed compilation is unsolvable. We empirically verify robustness in multiple domains using state-of-the-art numeric planners. Additionally, this compilation raises a challenge by generating a set of non-trivial numeric domains where unsolvability should be either proved or disproved.


#19 Expressive Optimal Temporal Planning via Optimization Modulo Theory [PDF1] [Copy] [Kimi] [REL]

Authors: Stefan Panjkovic, Andrea Micheli

Temporal Planning is the problem of synthesizing a course of actions given a predictive model of a system subject to temporal constraints. This kind of planning finds natural applications in the automation of industrial processes and in robotics when the timing and deadlines are important. Finding any plan in temporal planning is often not enough as it is sometimes needed to optimize a certain objective function: particularly interesting are the minimization of the makespan and the optimization of the costs of actions. Despite the importance of the problem, only few works in the literature tackled the problem of optimal temporal planning because of the complicated intermix of planning and scheduling. In this paper, we address the problem of optimal temporal planning for a very expressive class of problems using a reduction of the bounded planning problem to Optimization Modulo Theory (OMT) a powerful discrete/continuous optimization framework. We theoretically and empirically show the expressive power of this approach and we set a baseline for future research in this area.


#20 Flexible Budgets in Restless Bandits: A Primal-Dual Algorithm for Efficient Budget Allocation [PDF1] [Copy] [Kimi] [REL]

Authors: Paula Rodriguez Diaz, Jackson A. Killian, Lily Xu, Arun Sai Suggala, Aparna Taneja, Milind Tambe

Restless multi-armed bandits (RMABs) are an important model to optimize allocation of limited resources in sequential decision-making settings. Typical RMABs assume the budget --- the number of arms pulled --- to be fixed for each step in the planning horizon. However, for realistic real-world planning, resources are not necessarily limited at each planning step; we may be able to distribute surplus resources in one round to an earlier or later round. In real-world planning settings, this flexibility in budget is often constrained to within a subset of consecutive planning steps, e.g., weekly planning of a monthly budget. In this paper we define a general class of RMABs with flexible budget, which we term F-RMABs, and provide an algorithm to optimally solve for them. We derive a min-max formulation to find optimal policies for F-RMABs and leverage gradient primal-dual algorithms to solve for reward-maximizing policies with flexible budgets. We introduce a scheme to sample expected gradients to apply primal-dual algorithms to the F-RMAB setting and make an otherwise computationally expensive approach tractable. Additionally, we provide heuristics that trade off solution quality for efficiency and present experimental comparisons of different F-RMAB solution approaches.


#21 Structurally Restricted Fragments of Numeric Planning – a Complexity Analysis [PDF1] [Copy] [Kimi] [REL]

Authors: Alexander Shleyfman, Daniel Gnad, Peter Jonsson

Numeric planning is known to be undecidable even under severe restrictions. Prior work has investigated the decidability boundaries by restricting the expressiveness of the planning formalism in terms of the numeric functions allowed in conditions and effects. We study a well-known restricted form of Hoffmann's simple numeric planning, which is undecidable. We analyze the complexity by imposing restrictions on the causal structure, exploiting a novel method for bounding variable domain sizes. First, we show that plan existence for tasks where all numeric variables are root nodes in the causal graph is in PSPACE. Second, we show that for tasks with only numeric leaf variables the problem is decidable, and that it is in PSPACE if the propositional state space has a fixed size. Our work lays a strong foundation for future investigations of structurally more complex tasks. From a practical perspective, our method allows to employ heuristics and methods that are geared towards finite variable domains (such as pattern database heuristics or decoupled search) to solve non-trivial families of numeric planning problems.


#22 Predicate Invention for Bilevel Planning [PDF1] [Copy] [Kimi] [REL]

Authors: Tom Silver, Rohan Chitnis, Nishanth Kumar, Willie McClinton, Tomás Lozano-Pérez, Leslie Kaelbling, Joshua B. Tenenbaum

Efficient planning in continuous state and action spaces is fundamentally hard, even when the transition model is deterministic and known. One way to alleviate this challenge is to perform bilevel planning with abstractions, where a high-level search for abstract plans is used to guide planning in the original transition space. Previous work has shown that when state abstractions in the form of symbolic predicates are hand-designed, operators and samplers for bilevel planning can be learned from demonstrations. In this work, we propose an algorithm for learning predicates from demonstrations, eliminating the need for manually specified state abstractions. Our key idea is to learn predicates by optimizing a surrogate objective that is tractable but faithful to our real efficient-planning objective. We use this surrogate objective in a hill-climbing search over predicate sets drawn from a grammar. Experimentally, we show across four robotic planning environments that our learned abstractions are able to quickly solve held-out tasks, outperforming six baselines.


#23 Smoothed Online Combinatorial Optimization Using Imperfect Predictions [PDF1] [Copy] [Kimi] [REL]

Authors: Kai Wang, Zhao Song, Georgios Theocharous, Sridhar Mahadevan

Smoothed online combinatorial optimization considers a learner who repeatedly chooses a combinatorial decision to minimize an unknown changing cost function with a penalty on switching decisions in consecutive rounds. We study smoothed online combinatorial optimization problems when an imperfect predictive model is available, where the model can forecast the future cost functions with uncertainty. We show that using predictions to plan for a finite time horizon leads to regret dependent on the total predictive uncertainty and an additional switching cost. This observation suggests choosing a suitable planning window to balance between uncertainty and switching cost, which leads to an online algorithm with guarantees on the upper and lower bounds of the cumulative regret. Empirically, our algorithm shows a significant improvement in cumulative regret compared to other baselines in synthetic online distributed streaming problems.


#24 Scalable Decision-Focused Learning in Restless Multi-Armed Bandits with Application to Maternal and Child Health [PDF1] [Copy] [Kimi] [REL]

Authors: Kai Wang, Shresth Verma, Aditya Mate, Sanket Shah, Aparna Taneja, Neha Madhiwalla, Aparna Hegde, Milind Tambe

This paper studies restless multi-armed bandit (RMAB) problems with unknown arm transition dynamics but with known correlated arm features. The goal is to learn a model to predict transition dynamics given features, where the Whittle index policy solves the RMAB problems using predicted transitions. However, prior works often learn the model by maximizing the predictive accuracy instead of final RMAB solution quality, causing a mismatch between training and evaluation objectives. To address this shortcoming, we propose a novel approach for decision-focused learning in RMAB that directly trains the predictive model to maximize the Whittle index solution quality. We present three key contributions: (i) we establish differentiability of the Whittle index policy to support decision-focused learning; (ii) we significantly improve the scalability of decision-focused learning approaches in sequential problems, specifically RMAB problems; (iii) we apply our algorithm to a previously collected dataset of maternal and child health to demonstrate its performance. Indeed, our algorithm is the first for decision-focused learning in RMAB that scales to real-world problem sizes.


#25 Neural TSP Solver with Progressive Distillation [PDF1] [Copy] [Kimi] [REL]

Authors: Dongxiang Zhang, Ziyang Xiao, Yuan Wang, Mingli Song, Gang Chen

Travelling salesman problem (TSP) is NP-Hard with exponential search space. Recently, the adoption of encoder-decoder models as neural TSP solvers has emerged as an attractive topic because they can instantly obtain near-optimal results for small-scale instances. Nevertheless, their training efficiency and solution quality degrade dramatically when dealing with large-scale problems. To address the issue, we propose a novel progressive distillation framework, by adopting curriculum learning to train TSP samples in increasing order of their problem size and progressively distilling high-level knowledge from small models to large models via a distillation loss. In other words, the trained small models are used as the teacher network to guide action selection when training large models. To accelerate training speed, we also propose a Delaunary-graph based action mask and a new attention-based decoder to reduce decoding cost. Experimental results show that our approach establishes clear advantages over existing encoder-decoder models in terms of training effectiveness and solution quality. In addition, we validate its usefulness as an initial solution generator for the state-of-the-art TSP solvers, whose probability of obtaining the optimal solution can be further improved in such a hybrid manner.