Related papers: Flow-Based Policy for Online Reinforcement Learnin…

A hallmark of modern large-scale machine learning techniques is the use of training objectives that provide dense supervision to intermediate computations, such as teacher forcing the next token in language models or denoising step-by-step…

Recent advancements in reinforcement learning (RL) demonstrate the significant potential in autonomous driving. Despite this promise, challenges such as the manual design of reward functions and low sample efficiency in complex environments…

A novel optimization approach is proposed for application to policy gradient methods and evolution strategies for reinforcement learning (RL). The procedure uses a computationally efficient Wasserstein natural gradient (WNG) descent that…

Likelihood-based policy gradient methods are the dominant approach for training robot control policies from rewards. These methods rely on differentiable action likelihoods, which constrain policy outputs to simple distributions like…

Balancing policy expressiveness with the exploration-exploitation trade-off is a core challenge in online Reinforcement Learning (RL). While Stochastic Differential Equation (SDE)-based diffusion policies can represent complex, multimodal…

In this paper, a new population-guided parallel learning scheme is proposed to enhance the performance of off-policy reinforcement learning (RL). In the proposed scheme, multiple identical learners with their own value-functions and…

The Generative Flow Network (GFlowNet) is a probabilistic framework in which an agent learns a stochastic policy and flow functions to sample objects proportionally to an unnormalized reward function. A number of recent works explored…

Offline-to-Online Reinforcement Learning (O2O RL) faces a critical dilemma in balancing the use of a fixed offline dataset with newly collected online experiences. Standard methods, often relying on a fixed data-mixing ratio, struggle to…

System optimal traffic routing can mitigate congestion by assigning routes for a portion of vehicles so that the total travel time of all vehicles in the transportation system can be reduced. However, achieving real-time optimal routing…

Humans have the ability to reuse previously learned policies to solve new tasks quickly, and reinforcement learning (RL) agents can do the same by transferring knowledge from source policies to a related target task. Transfer RL methods can…

Offline reinforcement learning (RL) allows robots to learn from offline datasets without risky exploration. Yet, offline RL's performance often hinges on a brittle trade-off between (1) return maximization, which can push policies outside…

Vision-Language-Action (VLA) models based on flow matching have shown excellent performance in general-purpose robotic manipulation tasks. However, the action accuracy of these models on complex downstream tasks is unsatisfactory. One…

Behavior Cloning (BC) has emerged as a highly effective paradigm for robot learning. However, BC lacks a self-guided mechanism for online improvement after demonstrations have been collected. Existing offline-to-online learning methods…

Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…

We study the problem of Offline Safe Reinforcement Learning (OSRL), where the goal is to learn a reward-maximizing policy from fixed data under a cumulative cost constraint. We propose a novel OSRL approach that frames the problem as a…

Flow $Q$-learning has recently been introduced to integrate learning from expert demonstrations into an actor-critic structure. Central to this innovation is the ``the one-step policy'' network, which is optimized through a $Q$-function…

In recent years, Artificial Neural Networks (ANNs) and Deep Learning have become increasingly popular across a wide range of scientific and technical fields, including Fluid Mechanics. While it will take time to fully grasp the…

Generative Flow Networks (GFlowNets) were developed to learn policies for efficiently sampling combinatorial candidates by interpreting their generative processes as trajectories in directed acyclic graphs. In the value-based training…

Many reinforcement learning (RL) tasks have discrete action spaces, but most generative policy methods based on diffusion and flow matching are designed for continuous control. Meanwhile, generative policies usually rely heavily on offline…

We present a computationally efficient framework, called $\texttt{FlowDRO}$, for solving flow-based distributionally robust optimization (DRO) problems with Wasserstein uncertainty sets while aiming to find continuous worst-case…