A Stackelberg congestion game (SCG) is a bilevel program in which a leader aims to maximize their own gain by anticipating and manipulating the equilibrium state at which followers settle by playing a congestion game. Large-scale SCGs are well known for their intractability and complexity. This study approaches SCGs through differentiable programming, which marries the latest developments in machine learning with conventional methodologies. The core idea centers on representing the lower-level equilibrium problem using an evolution path formed by the imitative logit dynamics. It enables the use of automatic differentiation over the evolution path towards equilibrium, leading to a double-loop gradient descent algorithm. We further show the fixation on the lower-level equilibrium may be a self-imposed computational obstacle. Instead, the leader may only look ahead along the followers' evolution path for a few steps, while updating their decisions in sync with the followers through a co-evolution process. The revelation gives rise to a single-loop algorithm that is more efficient in terms of both memory consumption and computation time. Through numerical experiments that cover a wide range of benchmark problems, we find the single-loop algorithm consistently strikes a good balance between solution quality and efficiency, outperforming not only the standard double-loop implementation but also other methods from the literature. Importantly, our results highlight both the wastefulness of "full anticipation" and the peril of "zero anticipation". If a quick-and-dirty heuristic is needed for solving a really large SCG, the proposed single-loop algorithm with a one-step look-ahead makes an ideal candidate.
相關內容
We study the constrained reinforcement learning problem, in which an agent aims to maximize the expected cumulative reward subject to a constraint on the expected total value of a utility function. In contrast to existing model-based approaches or model-free methods accompanied with a `simulator', we aim to develop the first model-free, simulator-free algorithm that achieves a sublinear regret and a sublinear constraint violation even in large-scale systems. To this end, we consider the episodic constrained Markov decision processes with linear function approximation, where the transition dynamics and the reward function can be represented as a linear function of some known feature mapping. We show that $\tilde{\mathcal{O}}(\sqrt{d^3H^3T})$ regret and $\tilde{\mathcal{O}}(\sqrt{d^3H^3T})$ constraint violation bounds can be achieved, where $d$ is the dimension of the feature mapping, $H$ is the length of the episode, and $T$ is the total number of steps. Our bounds are attained without explicitly estimating the unknown transition model or requiring a simulator, and they depend on the state space only through the dimension of the feature mapping. Hence our bounds hold even when the number of states goes to infinity. Our main results are achieved via novel adaptations of the standard LSVI-UCB algorithms. In particular, we first introduce primal-dual optimization into the LSVI-UCB algorithm to balance between regret and constraint violation. More importantly, we replace the standard greedy selection with respect to the state-action function in LSVI-UCB with a soft-max policy. This turns out to be key in establishing uniform concentration for the constrained case via its approximation-smoothness trade-off. We also show that one can achieve an even zero constraint violation while still maintaining the same order with respect to $T$.
Butterfly Optimization Algorithm (BOA) is a recent metaheuristic that has been used in several optimization problems. In this paper, we propose a new version of the algorithm (xBOA) based on the crossover operator and compare its results to the original BOA and 3 other variants recently introduced in the literature. We also proposed a framework for solving the unknown area exploration problem with energy constraints using metaheuristics in both single- and multi-robot scenarios. This framework allowed us to benchmark the performances of different metaheuristics for the robotics exploration problem. We conducted several experiments to validate this framework and used it to compare the effectiveness of xBOA with wellknown metaheuristics used in the literature through 5 evaluation criteria. Although BOA and xBOA are not optimal in all these criteria, we found that BOA can be a good alternative to many metaheuristics in terms of the exploration time, while xBOA is more robust to local optima; has better fitness convergence; and achieves better exploration rates than the original BOA and its other variants.
We propose fully-distributed algorithms for Nash equilibrium seeking in aggregative games over networks. We first consider the case where only local constraints are present and we design an algorithm combining, for each agent, (i) the projected pseudo-gradient descent and (ii) a tracking mechanism to locally reconstruct the aggregative variable. To handle coupling constraints arising in generalized settings, we propose another distributed algorithm based on (i) a recently emerged augmented primal-dual scheme and (ii) two tracking mechanisms to reconstruct, for each agent, both the aggregative variable and the coupling constraint satisfaction. Leveraging tools from singular perturbations analysis, we prove linear convergence to the Nash equilibrium for both schemes. Finally, we run extensive numerical simulations to confirm the effectiveness of our methods, also showing that they outperform the current state-of-the-art distributed equilibrium seeking algorithms.
Inverse problems constrained by partial differential equations (PDEs) play a critical role in model development and calibration. In many applications, there are multiple uncertain parameters in a model that must be estimated. However, high dimensionality of the parameters and computational complexity of the PDE solves make such problems challenging. A common approach is to reduce the dimension by fixing some parameters (which we will call auxiliary parameters) to a best estimate and use techniques from PDE-constrained optimization to estimate the other parameters. In this article, hyper-differential sensitivity analysis (HDSA) is used to assess the sensitivity of the solution of the PDE-constrained optimization problem to changes in the auxiliary parameters. Foundational assumptions for HDSA require satisfaction of the optimality conditions which are not always practically feasible as a result of ill-posedness in the inverse problem. We introduce novel theoretical and computational approaches to justify and enable HDSA for ill-posed inverse problems by projecting the sensitivities on likelihood informed subspaces and defining a posteriori updates. Our proposed framework is demonstrated on a nonlinear multi-physics inverse problem motivated by estimation of spatially heterogenous material properties in the presence of spatially distributed parametric modeling uncertainties.
In the last decade, global cloud wide-area networks (WANs) have grown 10$\times$ in size due to the deployment of new network sites and datacenters, making it challenging for commercial optimization engines to solve the network traffic engineering (TE) problem within the temporal budget of a few minutes. In this work, we show that carefully designed deep learning models are key to accelerating the running time of intra-WAN TE systems for large deployments since deep learning is both massively parallel and it benefits from the wealth of historical traffic allocation data from production WANs. However, off-the-shelf deep learning methods fail to perform well on the TE task since they ignore the effects of network connectivity on flow allocations. They are also faced with a tractability challenge posed by the large problem scale of TE optimization. Moreover, neural networks do not have mechanisms to readily enforce hard constraints on model outputs (e.g., link capacity constraints). We tackle these challenges by designing a deep learning-based TE system -- Teal. First, Teal leverages graph neural networks (GNN) to faithfully capture connectivity and model network flows. Second, Teal devises a multi-agent reinforcement learning (RL) algorithm to process individual demands independently in parallel to lower the problem scale. Finally, Teal reduces link capacity violations and improves solution quality using the alternating direction method of multipliers (ADMM). We evaluate Teal on traffic matrices of a global commercial cloud provider and find that Teal computes near-optimal traffic allocations with a 59$\times$ speedup over state-of-the-art TE systems on a WAN topology of over 1,500 nodes.
This paper investigates when one can efficiently recover an approximate Nash Equilibrium (NE) in offline congestion games.The existing dataset coverage assumption in offline general-sum games inevitably incurs a dependency on the number of actions, which can be exponentially large in congestion games. We consider three different types of feedback with decreasing revealed information. Starting from the facility-level (a.k.a., semi-bandit) feedback, we propose a novel one-unit deviation coverage condition and give a pessimism-type algorithm that can recover an approximate NE. For the agent-level (a.k.a., bandit) feedback setting, interestingly, we show the one-unit deviation coverage condition is not sufficient. On the other hand, we convert the game to multi-agent linear bandits and show that with a generalized data coverage assumption in offline linear bandits, we can efficiently recover the approximate NE. Lastly, we consider a novel type of feedback, the game-level feedback where only the total reward from all agents is revealed. Again, we show the coverage assumption for the agent-level feedback setting is insufficient in the game-level feedback setting, and with a stronger version of the data coverage assumption for linear bandits, we can recover an approximate NE. Together, our results constitute the first study of offline congestion games and imply formal separations between different types of feedback.
Traffic signal control has the potential to reduce congestion in dynamic networks. Recent studies show that traffic signal control with reinforcement learning (RL) methods can significantly reduce the average waiting time. However, a shortcoming of existing methods is that they require model retraining for new intersections with different structures. In this paper, we propose a novel reinforcement learning approach with augmented data (ADLight) to train a universal model for intersections with different structures. We propose a new agent design incorporating features on movements and actions with set current phase duration to allow the generalized model to have the same structure for different intersections. A new data augmentation method named \textit{movement shuffle} is developed to improve the generalization performance. We also test the universal model with new intersections in Simulation of Urban MObility (SUMO). The results show that the performance of our approach is close to the models trained in a single environment directly (only a 5% loss of average waiting time), and we can reduce more than 80% of training time, which saves a lot of computational resources in scalable operations of traffic lights.
We propose an efficient way of solving optimal control problems for rigid-body systems on the basis of inverse dynamics and the multiple-shooting method. We treat all variables, including the state, acceleration, and control input torques, as optimization variables and treat the inverse dynamics as an equality constraint. We eliminate the update of the control input torques from the linear equation of Newton's method by applying condensing for inverse dynamics. The size of the resultant linear equation is the same as that of the multiple-shooting method based on forward dynamics except for the variables related to the passive joints and contacts. Compared with the conventional methods based on forward dynamics, the proposed method reduces the computational cost of the dynamics and their sensitivities by utilizing the recursive Newton-Euler algorithm (RNEA) and its partial derivatives. In addition, it increases the sparsity of the Hessian of the Karush-Kuhn-Tucker conditions, which reduces the computational cost, e.g., of Riccati recursion. Numerical experiments show that the proposed method outperforms state-of-the-art implementations of differential dynamic programming based on forward dynamics in terms of computational time and numerical robustness.
Bilevel optimization recently has received tremendous attention due to its great success in solving important machine learning problems like meta learning, reinforcement learning, and hyperparameter optimization. Extending single-agent training on bilevel problems to the decentralized setting is a natural generalization, and there has been a flurry of work studying decentralized bilevel optimization algorithms. However, it remains unknown how to design the distributed algorithm with sample complexity and convergence rate comparable to SGD for stochastic optimization, and at the same time without directly computing the exact Hessian or Jacobian matrices. In this paper we propose such an algorithm. More specifically, we propose a novel decentralized stochastic bilevel optimization (DSBO) algorithm that only requires first order stochastic oracle, Hessian-vector product and Jacobian-vector product oracle. The sample complexity of our algorithm matches the currently best known results for DSBO, and the advantage of our algorithm is that it does not require estimating the full Hessian and Jacobian matrices, thereby having improved per-iteration complexity.
Many real-world strategic games involve interactions between multiple players. We study a hierarchical multi-player game structure, where players with asymmetric roles can be separated into leaders and followers, a setting often referred to as Stackelberg game or leader-follower game. In particular, we focus on a Stackelberg game scenario where there are multiple leaders and a single follower, called the Multi-Leader-Single-Follower (MLSF) game. We propose a novel asymmetric equilibrium concept for the MLSF game called Correlated Stackelberg Equilibrium (CSE). We design online learning algorithms that enable the players to interact in a distributed manner, and prove that it can achieve no-external Stackelberg-regret learning. This further translates to the convergence to approximate CSE via a reduction from no-external regret to no-swap regret. At the core of our works, we solve the intricate problem of how to learn equilibrium in leader-follower games with noisy bandit feedback by balancing exploration and exploitation in different learning structures.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191