相关论文: Learning Quadrotor Control From Visual Features Us…

Model-based reinforcement learning (RL) has proven to be a data efficient approach for learning control tasks but is difficult to utilize in domains with complex observations such as images. In this paper, we present a method for learning…

The goal of this paper is to make a strong point for the usage of dynamical models when using reinforcement learning (RL) for feedback control of dynamical systems governed by partial differential equations (PDEs). To breach the gap between…

Deep reinforcement learning can generate complex control policies, but requires large amounts of training data to work effectively. Recent work has attempted to address this issue by leveraging differentiable simulators. However, inherent…

Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes…

In recent times, reinforcement learning has produced baffling results when it comes to performing control tasks with highly non-linear systems. The impressive results always outweigh the potential vulnerabilities or uncertainties associated…

Training an agent to solve control tasks directly from high-dimensional images with model-free reinforcement learning (RL) has proven difficult. A promising approach is to learn a latent representation together with the control policy.…

Although deep reinforcement learning (DRL) algorithms have made important achievements in many control tasks, they still suffer from the problems of sample inefficiency and unstable training process, which are usually caused by sparse…

Current control algorithms for aerial robots struggle with robustness in dynamic environments and adverse conditions. Model-based reinforcement learning (RL) has shown strong potential in handling these challenges while remaining…

Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…

Deep Reinforcement Learning (DRL) experiments are commonly performed in simulated environments due to the tremendous training sample demands from deep neural networks. In contrast, model-based Bayesian Learning allows a robot to learn good…

Deep neural network based reinforcement learning (RL) can learn appropriate visual representations for complex tasks like vision-based robotic grasping without the need for manually engineering or prior learning a perception system.…

In the last decade, data-driven approaches have become popular choices for quadrotor control, thanks to their ability to facilitate the adaptation to unknown or uncertain flight conditions. Among the different data-driven paradigms, Deep…

Improving sampling efficiency and generalization capability is critical for the successful data-driven control of quadrotor unmanned aerial vehicles (UAVs) that are inherently unstable. While various reinforcement learning (RL) approaches…

Current end-to-end deep Reinforcement Learning (RL) approaches require jointly learning perception, decision-making and low-level control from very sparse reward signals and high-dimensional inputs, with little capability of incorporating…

Offline reinforcement learning (RL) provides a promising approach to avoid costly online interaction with the real environment. However, the performance of offline RL highly depends on the quality of the datasets, which may cause…

Recent advances in behavior cloning (BC) have enabled impressive visuomotor control policies. However, these approaches are limited by the quality of human demonstrations, the manual effort required for data collection, and the diminishing…

Learning from human demonstrations can facilitate automation but is risky because the execution of the learned policy might lead to collisions and other failures. Adding explicit constraints to avoid unsafe states is generally not possible…

Training robots to perform complex control tasks from high-dimensional pixel input using reinforcement learning (RL) is sample-inefficient, because image observations are comprised primarily of task-irrelevant information. By contrast,…

Humans are remarkably data-efficient when adapting to new unseen conditions, like driving a new car. In contrast, modern robotic control systems, like neural network policies trained using Reinforcement Learning (RL), are highly specialized…

Reinforcement learning (RL) has been successfully used to solve many continuous control tasks. Despite its impressive results however, fundamental questions regarding the sample complexity of RL on continuous problems remain open. We study…