Related papers: TMRL: Diffusion Timestep-Modulated Pretraining Ena…

Robotic control policies learned from human demonstrations have achieved impressive results in many real-world applications. However, in scenarios where initial performance is not satisfactory, as is often the case in novel open-world…

Robotic manipulation policies are commonly initialized through imitation learning, but their performance is limited by the scarcity and narrow coverage of expert data. Reinforcement learning can refine polices to alleviate this limitation,…

Pretrained imitation policies have become a strong foundation for robot manipulation, but they often require online improvement to overcome execution errors, limited dataset coverage, and deployment mismatch. A central question is therefore…

In the field of legged robot motion control, reinforcement learning (RL) holds great promise but faces two major challenges: high computational cost for training individual robots and poor generalization of trained models. To address these…

We study online fine-tuning of pretrained control policies for autonomous driving using Real-Time Recurrent Reinforcement Learning (RTRRL), a memory-efficient algorithm that updates policy parameters at every time step without…

Model-free continuous control for robot navigation tasks using Deep Reinforcement Learning (DRL) that relies on noisy policies for exploration is sensitive to the density of rewards. In practice, robots are usually deployed in cluttered…

Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discrete diffusion models as highly effective policies in these…

We address the problem of fine-tuning pre-trained generative policies with reinforcement learning (RL) while preserving the multimodality of their action distributions. Existing methods for RL fine-tuning of generative policies (e.g.,…

Offline reinforcement learning (RL) methods harness previous experiences to derive an optimal policy, forming the foundation for pre-trained large-scale models (PLMs). When encountering tasks not seen before, PLMs often utilize several…

Standard practice across domains from robotics to language is to first pretrain a policy on a large-scale demonstration dataset, and then finetune this policy, typically with reinforcement learning (RL), in order to improve performance on…

Recent research has highlighted the powerful capabilities of imitation learning in robotics. Leveraging generative models, particularly diffusion models, these approaches offer notable advantages such as strong multi-task generalization,…

Reinforcement learning (RL) has demonstrated remarkable capability in acquiring robot skills, but learning each new skill still requires substantial data collection for training. The pretrain-and-finetune paradigm offers a promising…

Modeling generalized robot control policies poses ongoing challenges for language-guided robot manipulation tasks. Existing methods often struggle to efficiently utilize cross-dataset resources or rely on resource-intensive vision-language…

Thanks to their remarkable flexibility, diffusion models and flow models have emerged as promising candidates for policy representation. However, efficient reinforcement learning (RL) upon these policies remains a challenge due to the lack…

The growing demand for parking has increased the need for automated parking planning methods that can operate reliably in confined spaces. In restricted and complex environments, high-precision maneuvers are required to achieve a high…

Researchers have demonstrated that Deep Reinforcement Learning (DRL) is a powerful tool for finding policies that perform well on complex robotic systems. However, these policies are often unpredictable and can induce highly variable…

This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. While diffusion models are widely known to provide excellent generative modeling capability, practical…

Diffusion models have achieved remarkable success in text-to-image generation. However, their practical applications are hindered by the misalignment between generated images and corresponding text prompts. To tackle this issue,…

Developing robust autonomous loco-manipulation skills for humanoids remains an open problem in robotics. While RL has been applied successfully to legged locomotion, applying it to complex, interaction-rich manipulation tasks is harder…

Reinforcement learning (RL) is a powerful approach for robot learning. However, model-free RL (MFRL) requires a large number of environment interactions to learn successful control policies. This is due to the noisy RL training updates and…