We propose a deep reinforcement learning (RL) method to learn large neighborhood search (LNS) policy for integer programming (IP). The RL policy is trained as the destroy operator to select a subset of variables at each step, which is reoptimized by an IP solver as the repair operator. However, the combinatorial number of variable subsets prevents direct application of typical RL algorithms. To tackle this challenge, we represent all subsets by factorizing them into binary decisions on each variable. We then design a neural network to learn policies for each variable in parallel, trained by a customized actor-critic algorithm. We evaluate the proposed method on four representative IP problems. Results show that it can find better solutions than SCIP in much less time, and significantly outperform other LNS baselines with the same runtime. Moreover, these advantages notably persist when the policies generalize to larger problems. Further experiments with Gurobi also reveal that our method can outperform this state-of-the-art commercial solver within the same time limit.
Balans: Multi-Armed Bandits-based Adaptive Large Neighborhood Search for Mixed-Integer Programming Problem
Department of Computer Science, University of Southern California（南加州大学计算机科学系）；AI Center of Excellence, Fidelity Investments（富达投资人工智能卓越中心）；Department of Computer Science, Brown University（布朗大学计算机科学系）
VNU University of Engineering and Technology（越南国立大学工程技术大学）；Université de Montréal（蒙特利尔大学）；CIRRELT（企业物流研究中心）；École Polytechnique de Montréal（蒙特利尔综合理工学院）
We consider a vehicle routing problem which seeks to minimize cost subject to time window and synchronization constraints. In this problem, the fleet of vehicles is categorized into regular and special vehicles. Some customers require both vehicles' services, whose starting service times at the customer are synchronized. Despite its important real-world application, this problem has rarely been studied in the literature. To solve the problem, we propose a Constraint Programming (CP) model and an Adaptive Large Neighborhood Search (ALNS) in which the design of insertion operators is based on so…
Large Neighborhood Search (LNS) is a combinatorial optimization heuristic that starts with an assignment of values for the variables to be optimized, and iteratively improves it by searching a large neighborhood around the current assignment. In this paper we consider a learning-based LNS approach for mixed integer programs (MIPs). We train a Neural Diving model to represent a probability distribution over assignments, which, together with an off-the-shelf MIP solver, generates an initial assignment. Formulating the subsequent search steps as a Markov Decision Process, we train a Neural Neighb…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）
In this paper, we propose cautious policy programming (CPP), a novel value-based reinforcement learning (RL) algorithm that can ensure monotonic policy improvement during learning. Based on the nature of entropy-regularized RL, we derive a new entropy regularization-aware lower bound of policy improvement that only requires estimating the expected policy advantage function. CPP leverages this lower bound as a criterion for adjusting the degree of a policy update for alleviating policy oscillation. Different from similar algorithms that are mostly theory-oriented, we also propose a novel interp…
We consider the infinite-horizon discounted optimal control problem formalized by Markov Decision Processes. We focus on Policy Search algorithms, that compute an approximately optimal policy by following the standard Policy Iteration (PI) scheme via an -approximate greedy operator (Kakade and Langford, 2002; Lazaric et al., 2010). We describe existing and a few new performance bounds for Direct Policy Iteration (DPI) (Lagoudakis and Parr, 2003; Fern et al., 2006; Lazaric et al., 2010) and Conservative Policy Iteration (CPI) (Kakade and Langford, 2002). By paying a particular attention to the …
Shanghai Jiao Tong University（上海交通大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；University College London（伦敦大学学院）
Deriving a good variable selection strategy in branch-and-bound is essential for the efficiency of modern mixed-integer programming (MIP) solvers. With MIP branching data collected during the previous solution process, learning to branch methods have recently become superior over heuristics. As branch-and-bound is naturally a sequential decision making task, one should learn to optimize the utility of the whole MIP solving process instead of being myopic on each step. In this work, we formulate learning to branch as an offline reinforcement learning (RL) problem, and propose a long-sighted hyb…
Okinawa Institute of Science and Technology（冲绳科学技术大学院大学）；ATR Computational Neuroscience Laboratories（ATR计算神经科学实验室）
Approximate dynamic programming algorithms, such as approximate value iteration, have been successfully applied to many complex reinforcement learning tasks, and a better approximate dynamic programming algorithm is expected to further extend the applicability of reinforcement learning to various tasks. In this paper we propose a new, robust dynamic programming algorithm that unifies value iteration, advantage learning, and dynamic policy programming. We call it generalized value iteration (GVI) and its approximated version, approximate GVI (AGVI). We show AGVI's performance guarantee, which i…
This paper presents a constrained adaptive dynamic programming (CADP) algorithm to solve general nonlinear nonaffine optimal control problems with known dynamics. Unlike previous ADP algorithms, it can directly deal with problems with state constraints. Firstly, a constrained generalized policy iteration (CGPI) framework is developed to handle state constraints by transforming the traditional policy improvement process into a constrained policy optimization problem. Next, we propose an actor-critic variant of CGPI, called CADP, in which both policy and value functions are approximated by multi…
We consider infinite horizon dynamic programming problems, where the control at each stage consists of several distinct decisions, each one made by one of several agents. In an earlier work we introduced a policy iteration algorithm, where the policy improvement is done one-agent-at-a-time in a given order, with knowledge of the choices of the preceding agents in the order. As a result, the amount of computation for each policy improvement grows linearly with the number of agents, as opposed to exponentially for the standard all-agents-at-once method. For the case of a finite-state discounted …
Integer programming problems (IPs) are challenging to be solved efficiently due to the NP-hardness, especially for large-scale IPs. To solve this type of IPs, Large neighborhood search (LNS) uses an initial feasible solution and iteratively improves it by searching a large neighborhood around the current solution. However, LNS easily steps into local optima and ignores the correlation between variables to be optimized, leading to compromised performance. This paper presents a general adaptive constraint partition-based optimization framework (ACP) for large-scale IPs that can efficiently use a…
HyP-ASO: A Hybrid Policy-based Adaptive Search Optimization Framework for Large-Scale Integer Linear Programs
Ning Xu School of Mathematics and Statistics Nanjing University of Science and Technology（南京理工大学数学与统计学学院）；Junkai Zhang Institute of Automation Chinese Academy of Sciences（中国科学院自动化研究所）；Huigen Ye Department of Computer Science and Technology Tsinghua University（清华大学计算机科学与技术系）；Yang Wu Institute of Automation Chinese Academy of Sciences（中国科学院自动化研究所）；Hua Xu Department of Computer Science and Technology Tsinghua University（清华大学计算机科学与技术系）；Huiling Xu School of Mathematics and Statistics Nanjing University of Science and Technology（南京理工大学数学与统计学学院）；Yifan Zhang Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
A major challenge in the pharmaceutical industry is to design novel molecules with specific desired properties, especially when the property evaluation is costly. Here, we propose MNCE-RL, a graph convolutional policy network for molecular optimization with molecular neighborhood-controlled embedding grammars through reinforcement learning. We extend the original neighborhood-controlled embedding grammars to make them applicable to molecular graph generation and design an efficient algorithm to infer grammatical production rules from given molecules. The use of grammars guarantees the validity…
We consider the problem of controlling a fully specified Markov decision process (MDP), also known as the planning problem, when the state space is very large and calculating the optimal policy is intractable. Instead, we pursue the more modest goal of optimizing over some small family of policies. Specifically, we show that the family of policies associated with a low-dimensional approximation of occupancy measures yields a tractable optimization. Moreover, we propose an efficient algorithm, scaling with the size of the subspace but not the state space, that is able to find a policy with low …
Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions
Department of Mathematics, TU Darmstadt, Darmstadt, Germany（图腾达姆施塔特大学数学系）；Department of Electrical Engineering, TU Darmstadt, Darmstadt, Germany（图腾达姆施塔特大学电气工程系）
ParBalans: Parallel Multi-Armed Bandits-based Adaptive Large Neighborhood Search
Department of Mechanical & Industrial Engineering, Northeastern University（东北大学机械与工业工程系）；AI Center of Excellence, Fidelity Investments（fidelity investments 精英研究中心）；Department of Computer Science, University of Southern California（南加州大学计算机科学系）；Department of Computer Science, Brown University（布朗大学计算机科学系）
Microsoft Research（微软研究院）；IBM Research AI（IBM人工智能研究院）；Singapore Management University（新加坡管理大学）
We propose a framework, called neural-progressive hedging (NP), that leverages stochastic programming during the online phase of executing a reinforcement learning (RL) policy. The goal is to ensure feasibility with respect to constraints and risk-based objectives such as conditional value-at-risk (CVaR) during the execution of the policy, using probabilistic models of the state transitions to guide policy adjustments. The framework is particularly amenable to the class of sequential resource allocation problems since feasibility with respect to typical resource constraints cannot be enforced …
MIT（麻省理工学院）；University of Toronto（多伦多大学）；Toyota Research Institute（丰田研究院）
Experience replay plays a crucial role in improving the sample efficiency of deep reinforcement learning agents. Recent advances in experience replay propose using Mixup (Zhang et al., 2018) to further improve sample efficiency via synthetic sample generation. We build upon this technique with Neighborhood Mixup Experience Replay (NMER), a geometrically-grounded replay buffer that interpolates transitions with their closest neighbors in state-action space. NMER preserves a locally linear approximation of the transition manifold by only applying Mixup between transitions with vicinal state-acti…
Bin Packing with Conflicts (BPC) are problems in which items with compatibility constraints must be packed in the least number of bins, not exceeding the capacity of the bins and ensuring that non-conflicting items are packed in each bin. In this work, we introduce the Bin Packing Problem with Compatible Categories (BPCC), a variant of the BPC in which items belong to conflicting or compatible categories, in opposition to the item-by-item incompatibility found in previous literature. It is a common problem in the context of last mile distribution to nanostores located in densely populated area…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-尚佩恩分校）；Sandia National Laboratories（桑迪亚国家实验室）；c3.ai DTI
Function approximation is widely used in reinforcement learning to handle the computational difficulties associated with very large state spaces. However, function approximation introduces errors which may lead to instabilities when using approximate dynamic programming techniques to obtain the optimal policy. Therefore, techniques such as lookahead for policy improvement and m-step rollout for policy evaluation are used in practice to improve the performance of approximate dynamic programming with function approximation. We quantitatively characterize, for the first time, the impact of lookah…
California Institute of Technology（加州理工学院）；Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）
We study the problem of learning sequential decision-making policies in settings with multiple state-action representations. Such settings naturally arise in many domains, such as planning (e.g., multiple integer programming formulations) and various combinatorial optimization problems (e.g., those with both integer programming and graph-based formulations). Inspired by the classical co-training framework for classification, we study the problem of co-training for policy learning. We present sufficient conditions under which learning from two views can improve upon learning from a single view …
Deep Reinforcement Learning (DRL) is regarded as a potential method for car-following control and has been mostly studied to support a single following vehicle. However, it is more challenging to learn a stable and efficient car-following policy when there are multiple following vehicles in a platoon, especially with unpredictable leading vehicle behavior. In this context, we adopt an integrated DRL and Dynamic Programming (DP) approach to learn autonomous platoon control policies, which embeds the Deep Deterministic Policy Gradient (DDPG) algorithm into a finite-horizon value iteration framew…
Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems
King’s College London（伦敦国王学院）；Eindhoven University of Technology（埃因霍温理工大学）；University of California, San Diego（加州大学圣地亚哥分校）；The Alan Turing Institute（艾伦·图灵研究所）
Beijing Institute of Technology（北京理工大学）；Arizona State University（亚利桑那州立大学）
In this paper time-driven learning refers to the machine learning method that updates parameters in a prediction model continuously as new data arrives. Among existing approximate dynamic programming (ADP) and reinforcement learning (RL) algorithms, the direct heuristic dynamic programming (dHDP) has been shown an effective tool as demonstrated in solving several complex learning control problems. It continuously updates the control policy and the critic as system states continuously evolve. It is therefore desirable to prevent the time-driven dHDP from updating due to insignificant system eve…
In this paper we propose an on-line policy iteration (PI) algorithm for finite-state infinite horizon discounted dynamic programming, whereby the policy improvement operation is done on-line, only for the states that are encountered during operation of the system. This allows the continuous updating/improvement of the current policy, thus resulting in a form of on-line PI that incorporates the improved controls into the current policy as new states and controls are generated. The algorithm converges in a finite number of stages to a type of locally optimal policy, and suggests the possibility …
This note provides a simple example demonstrating that, if exact computations are allowed, the number of iterations required for the value iteration algorithm to find an optimal policy for discounted dynamic programming problems may grow arbitrarily quickly with the size of the problem. In particular, the number of iterations can be exponential in the number of actions. Thus, unlike policy iterations, the value iteration algorithm is not strongly polynomial for discounted dynamic programming.
Decisions in public health are almost always made in the context of uncertainty. Policy makers are responsible for making important decisions, faced with the daunting task of choosing from amongst many possible options. This task is called planning under uncertainty, and is particularly acute when addressing complex systems, such as issues of global health and development. Uncertainty leads to cautious or incorrect decisions that cost time, money, and human life. It is with this understanding that we pursue greater clarity on, and methods to address optimal policy making in health. Decision ma…
We propose a Large Neighborhood Search (LNS) approach utilizing a learned construction heuristic based on neural networks as repair operator to solve the vehicle routing problem with time windows (VRPTW). Our method uses graph neural networks to encode the problem and auto-regressively decodes a solution and is trained with reinforcement learning on the construction task without requiring any labels for supervision. The neural repair operator is combined with a local search routine, heuristic destruction operators and a selection procedure applied to a small population to arrive at a sophistic…
Motivated by the needs of resource constrained dialog policy learning, we introduce dialog policy via differentiable inductive logic (DILOG). We explore the tasks of one-shot learning and zero-shot domain transfer with DILOG on SimDial and MultiWoZ. Using a single representative dialog from the restaurant domain, we train DILOG on the SimDial dataset and obtain 99+% in-domain test accuracy. We also show that the trained DILOG zero-shot transfers to all other domains with 99+% accuracy, proving the suitability of DILOG to slot-filling dialogs. We further extend our study to the MultiWoZ dataset…
In this article, we consider the Virtual Network Embedding (VNE) problem for 5G networks slicing. This problem requires to allocate multiple Virtual Networks (VN) on a substrate virtualized physical network while maximizing among others, resource utilization, maximum number of placed VNs and network operator's benefit. We solve the online version of the problem where slices arrive over time. Inspired by the Nested Rollout Policy Adaptation (NRPA) algorithm, a variant of the well known Monte Carlo Tree Search (MCTS) that learns how to perform good simulations over time, we propose a new algorit…
We consider the problem of finding an n-agent joint-policy for the optimal finite-horizon control of a decentralized Pomdp (Dec-Pomdp). This is a problem of very high complexity (NEXP-hard in n >= 2). In this paper, we propose a new mathematical programming approach for the problem. Our approach is based on two ideas: First, we represent each agent's policy in the sequence-form and not in the tree-form, thereby obtaining a very compact representation of the set of joint-policies. Second, using this compact representation, we solve this problem as an instance of combinatorial optimization for w…
