Related papers: DiffusionRL: Efficient Training of Diffusion Polic…
Recent developments in offline reinforcement learning have uncovered the immense potential of diffusion modeling, which excels at representing heterogeneous behavior policies. However, sampling from diffusion policies is considerably slow…
Diffusion models, such as diffusion policy, have achieved state-of-the-art results in robotic manipulation by imitating expert demonstrations. While diffusion models were originally developed for vision tasks like image and video…
Generalizing locomotion policies across diverse legged robots with varying morphologies is a key challenge due to differences in observation/action dimensions and system dynamics. In this work, we propose Multi-Loco, a novel unified…
Offline reinforcement learning (RL), which aims to learn an optimal policy using a previously collected static dataset, is an important paradigm of RL. Standard RL methods often perform poorly in this regime due to the function…
We propose DemoDiffusion, a simple method for enabling robots to perform manipulation tasks by imitating a single human demonstration, without requiring task-specific training or paired human-robot data. Our approach is based on two…
Grasping objects successfully from a single-view camera is crucial in many robot manipulation tasks. An approach to solve this problem is to leverage simulation to create large datasets of pairs of objects and grasp poses, and then learn a…
Unmanned Aerial Vehicles (UAVs) are increasingly adopted in modern communication networks. However, challenges in decision-making and digital modeling continue to impede their rapid advancement. Reinforcement Learning (RL) algorithms face…
When transferring a Deep Reinforcement Learning model from simulation to the real world, the performance could be unsatisfactory since the simulation cannot imitate the real world well in many circumstances. This results in a long period of…
Recent advances in reinforcement learning (RL) have achieved great successes by leveraging the multimodality and exploration capability of diffusion policies. Among these approaches, one representative branch focuses on the sampling-based…
We introduce DreamControl, a novel methodology for learning autonomous whole-body humanoid skills. DreamControl leverages the strengths of diffusion models and Reinforcement Learning (RL): our core innovation is the use of a diffusion prior…
As a newly emerging advance in deep generative models, diffusion models have achieved state-of-the-art results in many fields, including computer vision, natural language processing, and molecule design. The remote sensing (RS) community…
Robotic dexterous manipulation is a challenging problem due to high degrees of freedom (DoFs) and complex contacts of multi-fingered robotic hands. Many existing deep reinforcement learning (DRL) based methods aim at improving sample…
Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with…
In this survey, we systematically summarize the current literature on studies that apply reinforcement learning (RL) to the motion planning and control of autonomous vehicles. Many existing contributions can be attributed to the pipeline…
Imitation learning provides an efficient way to teach robots dexterous skills; however, learning complex skills robustly and generalizablely usually consumes large amounts of human demonstrations. To tackle this challenging problem, we…
Diffusion Policy is a powerful technique tool for learning end-to-end visuomotor robot control. It is expected that Diffusion Policy possesses scalability, a key attribute for deep neural networks, typically suggesting that increasing model…
We apply reinforcement learning (RL) to robotics tasks. One of the drawbacks of traditional RL algorithms has been their poor sample efficiency. One approach to improve the sample efficiency is model-based RL. In our model-based RL…
Grasping is a fundamental robot skill, yet despite significant research advancements, learning-based 6-DOF grasping approaches are still not turnkey and struggle to generalize across different embodiments and in-the-wild settings. We build…
We propose Diffusion-Sharpening, a fine-tuning approach that enhances downstream alignment by optimizing sampling trajectories. Existing RL-based fine-tuning methods focus on single training timesteps and neglect trajectory-level alignment,…
Constrained reinforcement learning (RL) seeks high-performance policies under safety constraints. We focus on an offline setting where the agent has only a fixed dataset -- common in realistic tasks to prevent unsafe exploration. To address…