Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization

Optimizing complex and high-dimensional black-box functions is ubiquitous in science and engineering fields. Unfortunately, the online evaluation of these functions is restricted due to time and safety constraints in most cases. In offline model-based optimization (MBO), we aim to find a design that maximizes the target function using only a pre-existing offline dataset. While prior methods consider forward or inverse approaches to address the problem, these approaches are limited by conservatism and the difficulty of learning highly multi-modal mappings. Recently, there has been an emerging paradigm of learning to improve solutions with synthetic trajectories constructed from the offline dataset. In this paper, we introduce a novel conditional generative modeling approach to produce trajectories toward high-scoring regions. First, we construct synthetic trajectories toward high-scoring regions using the dataset while injecting locality bias for consistent improvement directions. Then, we train a conditional diffusion model to generate trajectories conditioned on their scores. Lastly, we sample multiple trajectories from the trained model with guidance to explore high-scoring regions beyond the dataset and select high-fidelity designs among generated trajectories with the proxy function. Extensive experiment results demonstrate that our method outperforms competitive baselines on Design-Bench and its practical variants. The code is publicly available in \texttt{https://github.com/dbsxodud-11/GTG}.

RouteFinder: Towards Foundation Models for Vehicle Routing Problems

Vehicle Routing Problems (VRPs) are optimization problems with significant real-world implications in logistics, transportation, and supply chain management. Despite the recent progress made in learning to solve individual VRP variants, there is a lack of a unified approach that can effectively tackle a wide range of tasks, which is crucial for real-world impact. This paper introduces RouteFinder, a framework for developing foundation models for VRPs. Our key idea is that a foundation model for VRPs should be able to model variants by treating each variant as a subset of a larger VRP problem, equipped with different attributes. We introduce a parallelized environment that can handle any combination of attributes at the same time in a batched manner, and an efficient sampling procedure to train on a mix of problems at each optimization step that can greatly improve convergence robustness. We also introduce novel Global Feature Embeddings that project instance-wise attributes efficiently onto the latent space and help the model understand different VRP variants. Finally, we introduce Efficient Adapter Layers, a simple yet effective technique to finetune pre-trained RouteFinder models to solve novel variants with previously unseen attributes outside of the original feature space. We validate our approach through extensive experiments on 24 VRP variants, demonstrating competitive results over recent multi-task learning models. We make our code openly available at https://github.com/ai4co/routefinder.

Distributed Online Planning for Min-Max Problems in Networked Markov Games

Min-max problems are important in multi-agent sequential decision-making because they improve the performance of the worst-performing agent in the network. However, solving the multi-agent min-max problem is challenging. We propose a modular, distributed, online planning-based algorithm that is able to approximate the solution of the min-max objective in networked Markov games, assuming that the agents communicate within a network topology and the transition and reward functions are neighborhood-dependent. This set-up is encountered in the multi-robot setting. Our method consists of two phases at every planning step. In the first phase, each agent obtains sample returns based on its local reward function, by performing online planning. Using the samples from online planning, each agent constructs a concave approximation of its underlying local return as a function of only the action of its neighborhood at the next planning step. In the second phase, the agents deploy a distributed optimization framework that converges to the optimal immediate next action for each agent, based on the function approximations of the first phase. We demonstrate our algorithm's performance through formation control simulations.

GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning

Offline Reinforcement Learning (Offline RL) presents challenges of learning effective decision-making policies from static datasets without any online interactions. Data augmentation techniques, such as noise injection and data synthesizing, aim to improve Q-function approximation by smoothing the learned state-action region. However, these methods often fall short of directly improving the quality of offline datasets, leading to suboptimal results. In response, we introduce \textbf{GTA}, Generative Trajectory Augmentation, a novel generative data augmentation approach designed to enrich offline data by augmenting trajectories to be both high-rewarding and dynamically plausible. GTA applies a diffusion model within the data augmentation framework. GTA partially noises original trajectories and then denoises them with classifier-free guidance via conditioning on amplified return value. Our results show that GTA, as a general data augmentation strategy, enhances the performance of widely used offline RL algorithms in both dense and sparse reward settings. Furthermore, we conduct a quality analysis of data augmented by GTA and demonstrate that GTA improves the quality of the data. Our code is available at https://github.com/Jaewoopudding/GTA

Pessimistic Backward Policy for GFlowNets

This paper studies Generative Flow Networks (GFlowNets), which learn to sample objects proportionally to a given reward function through the trajectory of state transitions. In this work, we observe that GFlowNets tend to under-exploit the high-reward objects due to training on insufficient number of trajectories, which may lead to a large gap between the estimated flow and the (known) reward value. In response to this challenge, we propose a pessimistic backward policy for GFlowNets (PBP-GFN), which maximizes the observed flow to align closely with the true reward for the object. We extensively evaluate PBP-GFN across eight benchmarks, including hyper-grid environment, bag generation, structured set generation, molecular generation, and four RNA sequence generation tasks. In particular, PBP-GFN enhances the discovery of high-reward objects, maintains the diversity of the objects, and consistently outperforms existing methods.

Ensembling Prioritized Hybrid Policies for Multi-agent Pathfinding

Multi-Agent Reinforcement Learning (MARL) based Multi-Agent Path Finding (MAPF) has recently gained attention due to its efficiency and scalability. Several MARL-MAPF methods choose to use communication to enrich the information one agent can perceive. However, existing works still struggle in structured environments with high obstacle density and a high number of agents. To further improve the performance of the communication-based MARL-MAPF solvers, we propose a new method, Ensembling Prioritized Hybrid Policies (EPH). We first propose a selective communication block to gather richer information for better agent coordination within multi-agent environments and train the model with a Q-learning-based algorithm. We further introduce three advanced inference strategies aimed at bolstering performance during the execution phase. First, we hybridize the neural policy with single-agent expert guidance for navigating conflict-free zones. Secondly, we propose Q value-based methods for prioritized resolution of conflicts as well as deadlock situations. Finally, we introduce a robust ensemble method that can efficiently collect the best out of multiple possible solutions. We empirically evaluate EPH in complex multi-agent environments and demonstrate competitive performance against state-of-the-art neural methods for MAPF.

Ant Colony Sampling with GFlowNets for Combinatorial Optimization

This paper introduces the Generative Flow Ant Colony Sampler (GFACS), a novel neural-guided meta-heuristic algorithm for combinatorial optimization. GFACS integrates generative flow networks (GFlowNets) with the ant colony optimization (ACO) methodology. GFlowNets, a generative model that learns a constructive policy in combinatorial spaces, enhance ACO by providing an informed prior distribution of decision variables conditioned on input graph instances. Furthermore, we introduce a novel combination of training tricks, including search-guided local exploration, energy normalization, and energy shaping to improve GFACS. Our experimental results demonstrate that GFACS outperforms baseline ACO algorithms in seven CO tasks and is competitive with problem-specific heuristics for vehicle routing problems. The source code is available at \url{https://github.com/ai4co/gfacs}.

ELA: Exploited Level Augmentation for Offline Learning in Zero-Sum Games

Offline learning has become widely used due to its ability to derive effective policies from offline datasets gathered by expert demonstrators without interacting with the environment directly. Recent research has explored various ways to enhance offline learning efficiency by considering the characteristics (e.g., expertise level or multiple demonstrators) of the dataset. However, a different approach is necessary in the context of zero-sum games, where outcomes vary significantly based on the strategy of the opponent. In this study, we introduce a novel approach that uses unsupervised learning techniques to estimate the exploited level of each trajectory from the offline dataset of zero-sum games made by diverse demonstrators. Subsequently, we incorporate the estimated exploited level into the offline learning to maximize the influence of the dominant strategy. Our method enables interpretable exploited level estimation in multiple zero-sum games and effectively identifies dominant strategy data. Also, our exploited level augmented offline learning significantly enhances the original offline learning algorithms including imitation learning and offline reinforcement learning for zero-sum games.

HiMAP: Learning Heuristics-Informed Policies for Large-Scale Multi-Agent Pathfinding

Large-scale multi-agent pathfinding (MAPF) presents significant challenges in several areas. As systems grow in complexity with a multitude of autonomous agents operating simultaneously, efficient and collision-free coordination becomes paramount. Traditional algorithms often fall short in scalability, especially in intricate scenarios. Reinforcement Learning (RL) has shown potential to address the intricacies of MAPF; however, it has also been shown to struggle with scalability, demanding intricate implementation, lengthy training, and often exhibiting unstable convergence, limiting its practical application. In this paper, we introduce Heuristics-Informed Multi-Agent Pathfinding (HiMAP), a novel scalable approach that employs imitation learning with heuristic guidance in a decentralized manner. We train on small-scale instances using a heuristic policy as a teacher that maps each single agent observation information to an action probability distribution. During pathfinding, we adopt several inference techniques to improve performance. With a simple training scheme and implementation, HiMAP demonstrates competitive results in terms of success rate and scalability in the field of imitation-learning-only MAPF, showing the potential of imitation-learning-only MAPF equipped with inference techniques.

Anfinsen Goes Neural: a Graphical Model for Conditional Antibody Design

Antibody design plays a pivotal role in advancing therapeutics. Although deep learning has made rapid progress in this field, existing methods make limited use of general protein knowledge and assume a graphical model (GM) that violates empirical findings on proteins. To address these limitations, we present Anfinsen Goes Neural (AGN), a graphical model that uses a pre-trained protein language model (pLM) and encodes a seminal finding on proteins called Anfinsen's dogma. Our framework follows a two-step process of sequence generation with pLM and structure prediction with graph neural network (GNN). Experiments show that our approach outperforms state-of-the-art results on benchmark experiments. We also address a critical limitation of non-autoregressive models -- namely, that they tend to generate unrealistic sequences with overly repeating tokens. To resolve this, we introduce a composition-based regularization term to the cross-entropy objective that allows an efficient trade-off between high performance and low token repetition. We demonstrate that our approach establishes a Pareto frontier over the current state-of-the-art. Our code is available at https://github.com/lkny123/AGN.