Reinforcement Learning (RL) is a machine learning (ML) technique to learn sequential
decision-making in complex problems. RL is inspired by trial-and-error based human/animal …

Deep reinforcement learning (RL) algorithms are predominantly evaluated by comparing
their relative performance on a large suite of tasks. Most published results on deep RL …

We propose a novel, object-agnostic method for learning a universal policy for dexterous
object gras** from realistic point cloud observations and proprioceptive information under …

We present DrQ-v2, a model-free reinforcement learning (RL) algorithm for visual
continuous control. DrQ-v2 builds on DrQ, an off-policy actor-critic approach that uses data …

This paper shows that self-supervised visual pre-training from real-world images is effective
for learning motor control tasks from pixels. We first train the visual representations by …

Visual model-based reinforcement learning (RL) has the potential to enable sample-efficient
robot learning from visual observations. Yet the current approaches typically train a single …

In reinforcement learning (RL), it is easier to solve a task if given a good representation.
While deep RL should automatically acquire such good representations, prior work often …

Reinforcement learning has achieved great success in many applications. However, sample
efficiency remains a key challenge, with prominent methods requiring millions (or even …