Reinforcement learning algorithms typically struggle in the absence of a dense, well-shaped
reward function. Intrinsically motivated exploration methods address this limitation by …

This article is about deep learning (DL) and deep reinforcement learning (DRL) works
applied to robotics. Both tools have been shown to be successful in delivering data-driven …

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 …

The reinforcement learning (RL) research area is very active, with an important number of
new contributions, especially considering the emergent field of deep RL (DRL). However, a …

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 …

Recent unsupervised pre-training methods have shown to be effective on language and
vision domains by learning useful representations for multiple downstream tasks. In this …

We introduce a new unsupervised pre-training method for reinforcement learning called
APT, which stands for Active Pre-Training. APT learns behaviors and representations by …

We introduce a new unsupervised pretraining objective for reinforcement learning. During
the unsupervised reward-free pretraining phase, the agent maximizes mutual information …

Data efficiency is a key challenge for deep reinforcement learning. We address this problem
by using unlabeled data to pretrain an encoder which is then finetuned on a small amount of …

Deep Reinforcement Learning (RL) has emerged as a powerful paradigm to solve a range
of complex yet specific control tasks. Yet training generalist agents that can quickly adapt to …