Plasticity, the ability of a neural network to quickly change its predictions in response to new
information, is essential for the adaptability and robustness of deep reinforcement learning …

In this work we identify the dormant neuron phenomenon in deep reinforcement learning,
where an agent's network suffers from an increasing number of inactive neurons, thereby …

This work identifies a common flaw of deep reinforcement learning (RL) algorithms: a
tendency to rely on early interactions and ignore useful evidence encountered later …

In reinforcement learning (RL), representation learning is a proven tool for complex image-
based tasks, but is often overlooked for environments with low-level states, such as physical …

Artificial neural networks, deep-learning methods and the backpropagation algorithm form
the foundation of modern machine learning and artificial intelligence. These methods are …

In this paper, we characterize the behavior of canonical value-based deep reinforcement
learning (RL) approaches under varying degrees of non-stationarity. In particular, we …

A growing body of evidence suggests that neural networks employed in deep reinforcement
learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the …

Value functions are a central component of deep reinforcement learning (RL). These
functions, parameterized by neural networks, are trained using a mean squared error …

Learning tabula rasa, that is without any prior knowledge, is the prevalent workflow in
reinforcement learning (RL) research. However, RL systems, when applied to large-scale …

Underpinning the past decades of work on the design, initialization, and optimization of
neural networks is a seemingly innocuous assumption: that the network is trained on a\textit …