# Relational Deep Reinforcement Learning

## WHY?

Relational information is important in some reinforcement learning tasks.

## WHAT?

Relational information can be important source for high scores in reinforcement learning. To provide inductive bias for relational information, this paper appied self-attention(MHDPA) to the last layer of the convolution network that encode the state. Another multilayer perceptron(f_\theta$f_\theta$) is applied in parallel to each self-attended objects.

## So?

The agent achieved state-of-the-art result in Box-World and StarCrat2 Minigame.

## Critic

Good inductive bias for relational information which is useful for agent.

Powered by aiden