Humans possess a remarkable ability to make decisions within real-world environments that
are expansive, complex, and multidimensional. Human cognitive computational …

Networks are a general language for describing complex systems of interacting entities. In
the real world, a network always contains massive nodes, edges and additional complex …

Similar to humans, RL agents use interactive learning to successfully obtain satisfactory
decision strategies. However, in many cases, it is desirable to learn directly from …

Abstract We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep
reinforcement learning combining model-free and model-based aspects. In contrast to most …

Sequential decision making problems, such as structured prediction, robotic control, and
game playing, require a combination of planning policies and generalisation of those plans …

The combination of deep reinforcement learning and search at both training and test time is
a powerful paradigm that has led to a number of successes in single-agent settings and …

Monte Carlo tree search (MCTS) is a recently proposed search method that combines the
precision of tree search with the generality of random sampling. It has received considerable …

The game of Go has long been viewed as the most challenging of classic games for artificial
intelligence owing to its enormous search space and the difficulty of evaluating board …

This paper introduces a Monte-Carlo algorithm for online planning in large POMDPs. The
algorithm combines a Monte-Carlo update of the agent's belief state with a Monte-Carlo tree …

We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep
reinforcement learning combining model-free and model-based aspects. In contrast to most …