Abstract Pretrained Foundation Models (PFMs) are regarded as the foundation for various
downstream tasks across different data modalities. A PFM (eg, BERT, ChatGPT, GPT-4) is …

This paper reviews exploration techniques in deep reinforcement learning. Exploration
techniques are of primary importance when solving sparse reward problems. In sparse …

Through multi-agent competition, the simple objective of hide-and-seek, and standard
reinforcement learning algorithms at scale, we find that agents create a self-supervised …

In this article, we aim to provide a literature review of different formulations and approaches
to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We …

Reinforcement learning allows solving complex tasks, however, the learning tends to be task-
specific and the sample efficiency remains a challenge. We present Plan2Explore, a self …

We introduce an exploration bonus for deep reinforcement learning methods that is easy to
implement and adds minimal overhead to the computation performed. The bonus is the error …

Sequential decision making, commonly formalized as Markov Decision Process (MDP)
optimization, is an important challenge in artificial intelligence. Two key approaches to this …

Reinforcement learning algorithms rely on carefully engineering environment rewards that
are extrinsic to the agent. However, annotating each environment with hand-designed …

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

Efficient exploration is a long-standing problem in sensorimotor learning. Major advances
have been demonstrated in noise-free, non-stochastic domains such as video games and …