Online reinforcement learning (RL) fine-tunes diffusion models with black-box rewards, but reverse-process methods such as Flow-GRPO are limited in efficiency by poor credit assignment, while forward-process methods such as DiffusionNFT are efficient yet unstable without carefully tuned exponential-moving-average (EMA) off-policy training. We show that NFT-style objectives contain a hidden forward--reverse consistency force that joint positive--negative training cancels only partially, and that EMA stabilizes training through restoration rather than off-policy rollouts. We introduce DiffusionART (Diffusion Reinforcement with Aggregation-First Reward Tilting), which aggregates each prompt's rewards into a shared reward-improving direction for reverse-process states, removing the consistency force by construction, and adds a trust-region-masked second update for drift-adaptive restoration without EMA tuning. It requires no differentiable reward model, remains effective with fewer samples per prompt, and supports pairwise reward models (DiffusionART-Pairwise). Across image and video generation, DiffusionART trains efficiently and stably without per-task tuning. In particular, on HunyuanVideo-13B with equally weighted visual and motion quality rewards, DiffusionART reaches the late-stage mean reward levels of DiffusionNFT and Flow-GRPO-Fast with 12.02 and 11.72 times fewer GPU hours, respectively, while achieving 28.8% and 53.0% higher mean training rewards.
Huawei Technologies, Zurich Research Center（华为技术有限公司苏黎世研究中心）
Logic optimization is an NP-hard problem commonly approached through hand-engineered heuristics. We propose to combine graph convolutional networks with reinforcement learning and a novel, scalable node embedding method to learn which local transforms should be applied to the logic graph. We show that this method achieves a similar size reduction as ABC on smaller circuits and outperforms it by 1.5-1.75x on larger random graphs.
Supporting state-of-the-art AI research requires balancing rapid prototyping, ease of use, and quick iteration, with the ability to deploy experiments at a scale traditionally associated with production systems.Deep learning frameworks such as TensorFlow, PyTorch and JAX allow users to transparently make use of accelerators, such as TPUs and GPUs, to offload the more computationally intensive parts of training and inference in modern deep learning systems. Popular training pipelines that use these frameworks for deep learning typically focus on (un-)supervised learning. How to best train reinf…
Self-Composing Policies for Scalable Continual Reinforcement Learning
Department of Computer Science and Artificial Intelligence, University of the Basque Country UPV/EHU, Donostia-San Sebastian, Spain（计算机科学与人工智能系，巴斯克国家大学UPV/EHU，圣地亚哥-桑塞班西斯，西班牙）；Basque Center for Applied Mathematics (BCAM), Bilbao, Spain（应用数学巴斯克中心（BCAM），毕尔巴鄂，西班牙）
Bayesian inference over the reward presents an ideal solution to the ill-posed nature of the inverse reinforcement learning problem. Unfortunately current methods generally do not scale well beyond the small tabular setting due to the need for an inner-loop MDP solver, and even non-Bayesian methods that do themselves scale often require extensive interaction with the environment to perform well, being inappropriate for high stakes or costly applications such as healthcare. In this paper we introduce our method, Approximate Variational Reward Imitation Learning (AVRIL), that addresses both of t…
University of Toronto（多伦多大学）；New York University（纽约大学）；Vector Institute（向量研究所）
In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature. We extend the framework of natural policy gradient and propose to optimize both the actor and the critic using Kronecker-factored approximate curvature (K-FAC) with trust region; hence we call our method Actor Critic using Kronecker-Factored Trust Region (ACKTR). To the best of our knowledge, this is the first scalable trust region natural gradient method for actor-critic methods. It is also a method that learns non-trivial task…
Several low-bandwidth distributable black-box optimization algorithms in the family of finite differences such as Evolution Strategies have recently been shown to perform nearly as well as tailored Reinforcement Learning methods in some Reinforcement Learning domains. One shortcoming of these black-box methods is that they must collect information about the structure of the return function at every update, and can often employ only information drawn from a distribution centered around the current parameters. As a result, when these algorithms are distributed across many machines, a significant…
Scalable Reinforcement Learning for Virtual Machine Scheduling
School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）
The use of neural networks as function approximators has enabled many advances in reinforcement learning (RL). The generalization power of neural networks combined with advances in RL algorithms has reignited the field of artificial intelligence. Despite their power, neural networks are considered black boxes, and their use in safety-critical settings remains a challenge. Recently, neural network verification has emerged as a way to certify safety properties of networks. Verification is a hard problem, and it is difficult to scale to large networks such as the ones used in deep reinforcement l…
Deep Reinforcement Learning (DRL) underlies in a simulated environment and optimizes objective goals. By extending the conventional interaction scheme, this paper proffers gym-ds3, a scalable and reproducible open environment tailored for a high-fidelity Domain-Specific System-on-Chip (DSSoC) application. The simulation corroborates to schedule hierarchical jobs onto heterogeneous System-on-Chip (SoC) processors and bridges the system to reinforcement learning research. We systematically analyze the representative SoC simulator and discuss the primary challenging aspects that the system (1) co…
For those seeking healthcare advice online, AI based dialogue agents capable of interacting with patients to perform automatic disease diagnosis are a viable option. This application necessitates efficient inquiry of relevant disease symptoms in order to make accurate diagnosis recommendations. This can be formulated as a problem of sequential feature (symptom) selection and classification for which reinforcement learning (RL) approaches have been proposed as a natural solution. They perform well when the feature space is small, that is, the number of symptoms and diagnosable disease categorie…
We consider a team of reinforcement learning agents that concurrently operate in a common environment, and we develop an approach to efficient coordinated exploration that is suitable for problems of practical scale. Our approach builds on seed sampling (Dimakopoulou and Van Roy, 2018) and randomized value function learning (Osband et al., 2016). We demonstrate that, for simple tabular contexts, the approach is competitive with previously proposed tabular model learning methods (Dimakopoulou and Van Roy, 2018). With a higher-dimensional problem and a neural network value function representatio…
Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning
Nanyang Technical University（南阳技术大学）；Mila - Quebec AI Institute（魁北克AI研究所）；Université de Montréal（蒙特利尔大学）；University of Oxford（牛津大学）；The AGH University of Krakow（克拉科夫AGH大学）
BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning
Insilico Medicine Canada Inc.（英矽智能加拿大公司）；Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）；Polytechnique Montréal（蒙特利尔工业大学）；Insilico Medicine AI Limited（英矽智能人工智能有限公司）；CIFAR AI Chair（加拿大高级研究院人工智能主席项目）
Signal attenuation enables scalable decentralized multi-agent reinforcement learning over networks
Army Research Laboratory（陆军研究实验室）；U.S. Army DEVCOM Adelphi（美国陆军阿德福尔德 DEVCOM）；Industrial Engineering Dept. Purdue University（工业工程系 帕克维尔大学）；Oden Institute University of Texas, Austin（奥登研究所 德州大学奥斯汀）
GRASP Laboratory（GRASP实验室）；University of Pennsylvania（宾夕法尼亚大学）
In this paper, we explore using deep reinforcement learning for problems with multiple agents. Most existing methods for deep multi-agent reinforcement learning consider only a small number of agents. When the number of agents increases, the dimensionality of the input and control spaces increase as well, and these methods do not scale well. To address this, we propose casting the multi-agent reinforcement learning problem as a distributed optimization problem. Our algorithm assumes that for multi-agent settings, policies of individual agents in a given population live close to each other in p…
Informed and robust decision making in the face of uncertainty is critical for robots that perform physical tasks alongside people. We formulate this as Bayesian Reinforcement Learning over latent Markov Decision Processes (MDPs). While Bayes-optimality is theoretically the gold standard, existing algorithms do not scale well to continuous state and action spaces. Our proposal builds on the following insight: in the absence of uncertainty, each latent MDP is easier to solve. We first obtain an ensemble of experts, one for each latent MDP, and fuse their advice to compute a baseline policy. Nex…
Representation Learning Enables Scalable Multitask Deep Reinforcement Learning
Mila – Québec AI Institute（魁北克AI研究所）；Université de Montréal（蒙特利尔大学）；McGill University（麦吉尔大学）；CIFAR AI Chair（CIFAR人工智能 chair）；Google DeepMind（谷歌DeepMind）
It has long been recognized that multi-agent reinforcement learning (MARL) faces significant scalability issues due to the fact that the size of the state and action spaces are exponentially large in the number of agents. In this paper, we identify a rich class of networked MARL problems where the model exhibits a local dependence structure that allows it to be solved in a scalable manner. Specifically, we propose a Scalable Actor-Critic (SAC) method that can learn a near optimal localized policy for optimizing the average reward with complexity scaling with the state-action space size of loca…
Multi-agent reinforcement learning experiments and open-source training environments are typically limited in scale, supporting tens or sometimes up to hundreds of interacting agents. In this paper we demonstrate the use of Vogue, a high performance agent based model (ABM) framework. Vogue serves as a multi-agent training environment, supporting thousands to tens of thousands of interacting agents while maintaining high training throughput by running both the environment and reinforcement learning (RL) agents on the GPU. High performance multi-agent environments at this scale have the potentia…
Mila, Quebec AI Institute（米拉-魁北克人工智能研究所）；McGill University（麦吉尔大学）
Multi-agent adversarial inverse reinforcement learning (MA-AIRL) is a recent approach that applies single-agent AIRL to multi-agent problems where we seek to recover both policies for our agents and reward functions that promote expert-like behavior. While MA-AIRL has promising results on cooperative and competitive tasks, it is sample-inefficient and has only been validated empirically for small numbers of agents -- its ability to scale to many agents remains an open question. We propose a multi-agent inverse RL algorithm that is more sample-efficient and scalable than previous works. Specifi…
We develop a Multi-Agent Reinforcement Learning (MARL) method to learn scalable control policies for target tracking. Our method can handle an arbitrary number of pursuers and targets; we show results for tasks consisting up to 1000 pursuers tracking 1000 targets. We use a decentralized, partially-observable Markov Decision Process framework to model pursuers as agents receiving partial observations (range and bearing) about targets which move using fixed, unknown policies. An attention mechanism is used to parameterize the value function of the agents; this mechanism allows us to handle an ar…
Nanjing University（南京大学）；University of New South Wales（新南威尔士大学）
While reinforcement learning (RL) algorithms are achieving state-of-the-art performance in various challenging tasks, they can easily encounter catastrophic forgetting or interference when faced with lifelong streaming information. In the paper, we propose a scalable lifelong RL method that dynamically expands the network capacity to accommodate new knowledge while preventing past memories from being perturbed. We use a Dirichlet process mixture to model the non-stationary task distribution, which captures task relatedness by estimating the likelihood of task-to-cluster assignments and cluster…
Cornell University（康奈尔大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Ride-hailing services, such as Didi Chuxing, Lyft, and Uber, arrange thousands of cars to meet ride requests throughout the day. We consider a Markov decision process (MDP) model of a ride-hailing service system, framing it as a reinforcement learning (RL) problem. The simultaneous control of many agents (cars) presents a challenge for the MDP optimization because the action space grows exponentially with the number of cars. We propose a special decomposition for the MDP actions by sequentially assigning tasks to the drivers. The new actions structure resolves the scalability problem and enabl…
In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent maximum likelihood loss functions, while also being able to leverage off-policy data. Our proposed approach, which we refer to as advantage-weighted regression (AWR), consists of two standard supervised learning steps: one to regress onto target values for a value function, and another to regress onto weighted target actions for the policy. The method is simple and general, can ac…
Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous approaches require a separate, computationally expensive optimization procedure per instance, making them impractical for both large amounts of data and high-dimensional data. Moreover, these methods are often restricted to certain subclasses of machine learning models (e.g. differentiable or tree-based models). In this work, we propose a deep reinforcement learning…
This paper proposes a novel scalable reinforcement learning approach for simultaneous routing and spectrum access in wireless ad-hoc networks. In most previous works on reinforcement learning for network optimization, the network topology is assumed to be fixed, and a different agent is trained for each transmission node -- this limits scalability and generalizability. Further, routing and spectrum access are typically treated as separate tasks. Moreover, the optimization objective is usually a cumulative metric along the route, e.g., number of hops or delay. In this paper, we account for the …
Learning efficient and interpretable policies has been a challenging task in reinforcement learning (RL), particularly in the visual RL setting with complex scenes. While neural networks have achieved competitive performance, the resulting policies are often over-parameterized black boxes that are difficult to interpret and deploy efficiently. More recent symbolic RL frameworks have shown that high-level domain-specific programming logic can be designed to handle both policy learning and symbolic planning. However, these approaches rely on coded primitives with little feature learning, and whe…
Istanbul Technical University（伊斯坦布尔技术大学）；Artificial Intelligence and Data Science Application and Research Center（人工智能与数据科学应用研究中心）
In this work we propose a reinforcement learning (RL) framework that controls the density of a large-scale swarm for engaging with adversarial swarm attacks. Although there is a significant amount of existing work in applying artificial intelligence methods to swarm control, analysis of interactions between two adversarial swarms is a rather understudied area. Most of the existing work in this subject develop strategies by making hard assumptions regarding the strategy and dynamics of the adversarial swarm. Our main contribution is the formulation of the swarm to swarm engagement problem as a …
