相关论文: Robust Robotic Control from Pixels using Contrasti…

We study reinforcement learning (RL) in settings where observations are high-dimensional, but where an RL agent has access to abstract knowledge about the structure of the state space, as is the case, for example, when a robot is tasked to…

Despite the growing interest in robot control utilizing the computation of biological neurons, context-dependent behavior by neuron-connected robots remains a challenge. Context-dependent behavior here is defined as behavior that is not the…

We consider the problem of learning useful robotic skills from previously collected offline data without access to manually specified rewards or additional online exploration, a setting that is becoming increasingly important for scaling…

In this paper, we present a robotic model-based reinforcement learning method that combines ideas from model identification and model predictive control. We use a feature-based representation of the dynamics that allows the dynamics model…

Recent work has shown that representation learning plays a critical role in sample-efficient reinforcement learning (RL) from pixels. Unfortunately, in real-world scenarios, representation learning is usually fragile to task-irrelevant…

Recent progress in deep reinforcement learning (RL) and computer vision enables artificial agents to solve complex tasks, including locomotion, manipulation and video games from high-dimensional pixel observations. However, domain specific…

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of…

Multi-robot manipulation tasks involve various control entities that can be separated into dynamically independent parts. A typical example of such real-world tasks is dual-arm manipulation. Learning to naively solve such tasks with…

It is well-known that inverse dynamics models can improve tracking performance in robot control. These models need to precisely capture the robot dynamics, which consist of well-understood components, e.g., rigid body dynamics, and effects…

A generalist robot must be able to complete a variety of tasks in its environment. One appealing way to specify each task is in terms of a goal observation. However, learning goal-reaching policies with reinforcement learning remains a…

This work highlights that video world modeling, alongside vision-language pre-training, establishes a fresh and independent foundation for robot learning. Intuitively, video world models provide the ability to imagine the near future by…

Many real-world offline reinforcement learning (RL) problems involve continuous-time environments with delays. Such environments are characterized by two distinctive features: firstly, the state x(t) is observed at irregular time intervals,…

The use of learned dynamics models, also known as world models, can improve the sample efficiency of reinforcement learning. Recent work suggests that the underlying causal graphs of such dynamics models are sparsely connected, with each of…

Unsupervised learning has recently made exceptional progress because of the development of more effective contrastive learning methods. However, CNNs are prone to depend on low-level features that humans deem non-semantic. This dependency…

Navigation and guidance of autonomous vehicles is a fundamental problem in robotics, which has attracted intensive research in recent decades. This report is mainly concerned with provable collision avoidance of multiple autonomous vehicles…

Reinforcement learning (RL) agents need to explore their environment to learn optimal behaviors and achieve maximum rewards. However, exploration can be risky when training RL directly on real systems, while simulation-based training…

Reinforcement Learning (RL) is a method for learning decision-making tasks that could enable robots to learn and adapt to their situation on-line. For an RL algorithm to be practical for robotic control tasks, it must learn in very few…

We consider model-based reinforcement learning (MBRL) in 2-agent, high-fidelity continuous control problems -- an important domain for robots interacting with other agents in the same workspace. For non-trivial dynamical systems, MBRL…

Sampling-based methods have become a cornerstone of contemporary approaches to Model Predictive Control (MPC), as they make no restrictions on the differentiability of the dynamics or cost function and are straightforward to parallelize.…

Safe and compliant control of dynamic systems in interaction with the environment, e.g., in shared workspaces, continues to represent a major challenge. Mismatches in the dynamic model of the robots, numerical singularities, and the…