Learning to solve complex sequences of tasks--while both leveraging transfer and avoiding
catastrophic forgetting--remains a key obstacle to achieving human-level intelligence. The …

In this work we aim to solve a large collection of tasks using a single reinforcement learning
agent with a single set of parameters. A key challenge is to handle the increased amount of …

In recent years deep reinforcement learning (RL) systems have attained superhuman
performance in a number of challenging task domains. However, a major limitation of such …

Learning to navigate in complex environments with dynamic elements is an important
milestone in developing AI agents. In this work we formulate the navigation question as a …

Deep neural networks have achieved impressive successes in fields ranging from object
recognition to complex games such as Go 1 , 2 . Navigation, however, remains a substantial …

Over the past 20 years, neuroscience research on reward-based learning has converged
on a canonical model, under which the neurotransmitter dopamine ‘stamps in’associations …

The reinforcement learning (RL) community has made great strides in designing algorithms
capable of exceeding human performance on specific tasks. These algorithms are mostly …

We are increasingly surrounded by artificially intelligent technology that takes decisions and
executes actions on our behalf. This creates a pressing need for general means to …

Some of the most successful applications of deep reinforcement learning to challenging
domains in discrete and continuous control have used policy gradient methods in the on-policy …

This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve
hard exploration problems in partially observable environments with highly variable initial …