相关论文: Cold Diffusion on the Replay Buffer: Learning to P…

Self-play reinforcement learning has demonstrated significant success in learning complex strategic and interactive behaviors in competitive multi-agent games. However, achieving such behaviors in continuous decision spaces remains…

In the field of Robot Learning, the complex mapping between high-dimensional observations such as RGB images and low-level robotic actions, two inherently very different spaces, constitutes a complex learning problem, especially with…

Imitation Learning presents a promising approach for learning generalizable and complex robotic skills. The recently proposed Diffusion Policy generates robot action sequences through a conditional denoising diffusion process, achieving…

Learning a generalist embodied agent capable of completing multiple tasks poses challenges, primarily stemming from the scarcity of action-labeled robotic datasets. In contrast, a vast amount of human videos exist, capturing intricate tasks…

Learning from demonstration (LfD) has the potential to greatly increase the applicability of robotic manipulators in modern industrial applications. Recent progress in LfD methods have put more emphasis in learning robustness than in…

Temporal abstraction and efficient planning pose significant challenges in offline reinforcement learning, mainly when dealing with domains that involve temporally extended tasks and delayed sparse rewards. Existing methods typically plan…

Reinforcement Learning has been able to solve many complicated robotics tasks without any need for feature engineering in an end-to-end fashion. However, learning the optimal policy directly from the sensory inputs, i.e the observations,…

Safe, reliable navigation in extreme, unfamiliar terrain is required for future robotic space exploration missions. Recent generative-AI methods learn semantically aware navigation policies from large, cross-embodiment datasets, but offer…

Learning from Demonstration (LfD) systems are commonly used to teach robots new tasks by generating a set of skills from user-provided demonstrations. These skills can then be sequenced by planning algorithms to execute complex tasks.…

We introduce $\textbf{F}$uture $\textbf{LA}$tent $\textbf{RE}$presentation Alignment ($\textbf{FLARE}$), a novel framework that integrates predictive latent world modeling into robot policy learning. By aligning features from a diffusion…

Humans are able to seamlessly visually imitate others, by inferring their intentions and using past experience to achieve the same end goal. In other words, we can parse complex semantic knowledge from raw video and efficiently translate…

In partially observable multi-agent systems, agents typically only have access to local observations. This severely hinders their ability to make precise decisions, particularly during decentralized execution. To alleviate this problem and…

Imitation learning enables robots to learn from demonstrations. Previous imitation learning algorithms usually assume access to optimal expert demonstrations. However, in many real-world applications, this assumption is limiting. Most…

We describe a robust planning method for autonomous driving that mixes normal and adversarial agent predictions output by a diffusion model trained for motion prediction. We first train a diffusion model to learn an unbiased distribution of…

Federated Class Continual Learning (FCCL) merges the challenges of distributed client learning with the need for seamless adaptation to new classes without forgetting old ones. The key challenge in FCCL is catastrophic forgetting, an issue…

End-to-end learning of robot control policies, structured as neural networks, has emerged as a promising approach to robotic manipulation. To complete many common tasks, relevant objects are required to pass in and out of a robot's field of…

Reinforcement Learning (RL)-based motion planning has recently shown the potential to outperform traditional approaches from autonomous navigation to robot manipulation. In this work, we focus on a motion planning task for an evasive target…

This paper introduces Diffusion Policy, a new way of generating robot behavior by representing a robot's visuomotor policy as a conditional denoising diffusion process. We benchmark Diffusion Policy across 12 different tasks from 4…

Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…

State-of-the-art imitation learning from observation methods (ILfO) have recently made significant progress, but they still have some limitations: they need action-based supervised optimisation, assume that states have a single optimal…