Contrastive Learning has recently received interest due to its success in self-supervised
representation learning in the computer vision domain. However, the origins of Contrastive …

There has been an emerging paradigm shift from the era of “internet AI” to “embodied AI,”
where AI algorithms and agents no longer learn from datasets of images, videos or text …

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 …

While deep reinforcement learning excels at solving tasks where large amounts of data can
be collected through virtually unlimited interaction with the environment, learning from …

In an effort to overcome limitations of reward-driven feature learning in deep reinforcement
learning (RL) from images, we propose decoupling representation learning from policy …

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 …

Consider the following instance of the Offline Meta Reinforcement Learning (OMRL)
problem: given the complete training logs of $ N $ conventional RL agents, trained on $ N …

Learning a good representation is an essential component for deep reinforcement learning
(RL). Representation learning is especially important in multitask and partially observable …

Abstract ObjectGoal Navigation (ObjectNav) is an embodied task wherein agents are to
navigate to an object instance in an unseen environment. Prior works have shown that end …

In view of its power in extracting feature representation, contrastive self-supervised learning
has been successfully integrated into the practice of (deep) reinforcement learning (RL) …