Related papers: When Should We Prefer State-to-Visual DAgger Over …
This work considers two distinct settings: imitation learning and goal-conditioned reinforcement learning. In either case, effective solutions require the agent to reliably reach a specified state (a goal), or set of states (a…
Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and…
For a robotic grasping task in which diverse unseen target objects exist in a cluttered environment, some deep learning-based methods have achieved state-of-the-art results using visual input directly. In contrast, actor-critic deep…
Learning from previously collected data via behavioral cloning or offline reinforcement learning (RL) is a powerful recipe for scaling generalist agents by avoiding the need for expensive online learning. Despite strong generalization in…
Imitation learning (IL) has achieved considerable success in solving complex sequential decision-making problems. However, current IL methods mainly assume that the environment for learning policies is the same as the environment for…
Online reinforcement learning (RL) enhances policies through direct interactions with the environment, but faces challenges related to sample efficiency. In contrast, offline RL leverages extensive pre-collected data to learn policies, but…
Training end-to-end policies from image data to directly predict navigation actions for robotic systems has proven inherently difficult. Existing approaches often suffer from either the sim-to-real gap during policy transfer or a limited…
Reinforcement learning (RL) promises to enable autonomous acquisition of complex behaviors for diverse agents. However, the success of current reinforcement learning algorithms is predicated on an often under-emphasised requirement -- each…
A prevailing approach for learning visuomotor policies is to employ reinforcement learning to map high-dimensional visual observations directly to action commands. However, the combination of high-dimensional visual inputs and agile…
Pre-training for Reinforcement Learning (RL) with purely video data is a valuable yet challenging problem. Although in-the-wild videos are readily available and inhere a vast amount of prior world knowledge, the absence of action…
A prominent approach to visual Reinforcement Learning (RL) is to learn an internal state representation using self-supervised methods, which has the potential benefit of improved sample-efficiency and generalization through additional…
This work explores techniques to scale up image-based end-to-end learning for dexterous grasping with an arm + hand system. Unlike state-based RL, vision-based RL is much more memory inefficient, resulting in relatively low batch sizes,…
Visual navigation is essential for many applications in robotics, from manipulation, through mobile robotics to automated driving. Deep reinforcement learning (DRL) provides an elegant map-free approach integrating image processing,…
Reinforcement learning (RL) is a goal-oriented learning solution that has proven to be successful for Neural Architecture Search (NAS) on the CIFAR and ImageNet datasets. However, a limitation of this approach is its high computational…
While it is generally acknowledged that force feedback is beneficial to robotic control, applications of policy learning to robotic manipulation typically only leverage visual feedback. Recently, symmetric neural models have been used to…
Existing on-policy imitation learning algorithms, such as DAgger, assume access to a fixed supervisor. However, there are many settings where the supervisor may evolve during policy learning, such as a human performing a novel task or an…
Learning from visual observation (LfVO), aiming at recovering policies from only visual observation data, is promising yet a challenging problem. Existing LfVO approaches either only adopt inefficient online learning schemes or require…
The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new tasks. In this work, the tasks correspond to reward…
Reinforcement Learning (RL) based methods have seen their paramount successes in solving serial decision-making and control problems in recent years. For conventional RL formulations, Markov Decision Process (MDP) and state-action-value…
Automated visualization recommendations (vis-rec) help users to derive crucial insights from new datasets. Typically, such automated vis-rec models first calculate a large number of statistics from the datasets and then use machine-learning…