Notes
  • README
  • Roadmap
  • Graph
    • GraphSAGE
    • DiffPool
    • RRN
    • Relational RL
    • Layerwise Adaptive Sampling
    • Representation Lerning on Graphs: Methods and Applications
    • GAT
    • How Powerful are Graph Neural Networks?
    • Pitfalls of Graph Neural Network Evaluation
    • Spectral Networks and Deep Locally Connected Networks on Graphs
    • Deep Convolutional Networks on Graph-Structured Data
  • Optimizations
    • Neural ODE
  • Tags
Powered by GitBook
On this page
  • Structure
  • Feature Extraction
  • Relational Module
  • Policy and Value Network
  • Task
  • Box-World
  • Starcraft
  1. Graph

Relational RL

PreviousRRNNextLayerwise Adaptive Sampling

Last updated 6 years ago

TL;DR: RRL combine Reinforcement Learning with Relation Learning or Inductive Logic Programming by representing states, actions and policies using a first order(relational) language.

Structure

Feature Extraction

We apply a CNN on the raw image and get a feature map: where we have one $k$-dimension vector for each pixel(kkk is the number of output channels of CNN), the vector is then concatenated with xxx and yyy coordinates to indicate its position in the map.

We treat the resulting n2n^2n2 pixel-feature vectors as the set of entities.

Relational Module

The output is then passed to the relational module, where we iteratively apply "attention block" on entity representations:

The attention block is the same as a Multi-Head Attention module in Transformer.

img

Policy and Value Network

The output of relational module is aggregated via a feature-wise max-pooling across space(n×n×kn\times n \times kn×n×k tensor to a kkk-dimensional vector), the feature is then used to produce value and policy for Actor-Critic Algorithm.

Task

Box-World

  • Action: left, right, up, down.

  • pick up keys and open boxes(two adjacent colored pixels)

    • Agent could pick up loose keys(isolated colored pixel) and open boxes with corresponding locks.

    • Most boxes contain keys in then, and one box contain a gem(colored with white), the target of the game is to reach the gem.

Starcraft

img