We explore deep reinforcement learning methods for multi-agent domains. We begin by
analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged …

Patients with oral cancer can have high psychological distress levels, but the effects of stress-related
hormones on oral cancer cells and possible mechanisms underlying these …

For many applications of reinforcement learning it can be more convenient to specify both a
reward function and constraints, rather than trying to design behavior through the reward …

The substantia gelatinosa (SG) of the spinal dorsal horn shows significant morphological
heterogeneity and receives primary afferent input predominantly from Aδ‐ and C‐fibres. …

We introduce the value iteration network (VIN): a fully differentiable neural network with
aplanning module'embedded within. VINs can learn to plan, and are suitable for predicting …

Model-free reinforcement learning (RL) methods are succeeding in a growing number of
tasks, aided by recent advances in deep learning. However, they tend to suffer from high …

Managing risk in dynamic decision problems is of cardinal importance in many fields such as
finance and process control. The most common approach to defining risk is through various …

Dopaminergic innervation of the spinal cord is largely derived from the brain. To understand
the cellular mechanisms of antinociception mediated by descending dopaminergic pathways…

Recently, much attention has been devoted to the question of whether/when traditional network
protocol design, which relies on the application of algorithmic insights by human experts, …

We present an actor-critic framework for MDPs where the objective is the variance-adjusted
expected return. Our critic uses linear function approximation, and we extend the concept of …