Related papers: FAIL: Flow Matching Adversarial Imitation Learning…
Training a policy in a source domain for deployment in the target domain under a dynamics shift can be challenging, often resulting in performance degradation. Previous work tackles this challenge by training on the source domain with…
This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gradients through the differentiable generation process of flow matching. However,…
Few-shot imitation learning relies on only a small amount of task-specific demonstrations to efficiently adapt a policy for a given downstream tasks. Retrieval-based methods come with a promise of retrieving relevant past experiences to…
Generative policies based on diffusion models and flow matching have shown strong promise for offline reinforcement learning (RL), but their applicability remains largely confined to continuous action spaces. To address a broader range of…
Flow-matching models deliver state-of-the-art fidelity in image and video generation, but the inherent sequential denoising process renders them slower. Existing acceleration methods like distillation, trajectory truncation, and consistency…
Learning from demonstrations has made great progress over the past few years. However, it is generally data hungry and task specific. In other words, it requires a large amount of data to train a decent model on a particular task, and the…
Though impressive results have been achieved in visual captioning, the task of generating abstract stories from photo streams is still a little-tapped problem. Different from captions, stories have more expressive language styles and…
While Adversarial Imitation Learning (AIL) algorithms have recently led to state-of-the-art results on various imitation learning benchmarks, it is unclear as to what impact various design decisions have on performance. To this end, we…
Exemplar-free class-incremental learning (EFCIL) aims to retain old knowledge acquired in the previous task while learning new classes, without storing the previous images due to storage constraints or privacy concerns. In EFCIL, the…
We propose Flow-GRPO, the first method to integrate online policy gradient reinforcement learning (RL) into flow matching models. Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary…
In inverse reinforcement learning (IRL), an agent seeks to replicate expert demonstrations through interactions with the environment. Traditionally, IRL is treated as an adversarial game, where an adversary searches over reward models, and…
Sample efficiency is critical in solving real-world reinforcement learning problems, where agent-environment interactions can be costly. Imitation learning from expert advice has proved to be an effective strategy for reducing the number of…
Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function,…
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…
Many imitation learning (IL) algorithms use inverse reinforcement learning (IRL) to infer a reward function that aligns with the demonstration. However, the inferred reward functions often fail to capture the underlying task objectives. In…
Often times in imitation learning (IL), the environment we collect expert demonstrations in and the environment we want to deploy our learned policy in aren't exactly the same (e.g. demonstrations collected in simulation but deployment in…
Learning to imitate expert behavior from demonstrations can be challenging, especially in environments with high-dimensional, continuous observations and unknown dynamics. Supervised learning methods based on behavioral cloning (BC) suffer…
Imitation learning is well-suited for robotic tasks where it is difficult to directly program the behavior or specify a cost for optimal control. In this work, we propose a method for learning the reward function (and the corresponding…
Federated learning (FL) enables collaborative training of a global model in the centralized server with data from multiple parties while preserving privacy. However, data heterogeneity can significantly degrade the performance of the global…
Federated learning (FL) is an appealing paradigm that allows a group of machines (a.k.a. clients) to learn collectively while keeping their data local. However, due to the heterogeneity between the clients' data distributions, the model…