My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control

10/05/2020
by   Vitaly Kurin, et al.
7

Multitask Reinforcement Learning is a promising way to obtain models with better performance, generalisation, data efficiency, and robustness. Most existing work is limited to compatible settings, where the state and action space dimensions are the same across tasks. Graph Neural Networks (GNN) are one way to address incompatible environments, because they can process graphs of arbitrary size. They also allow practitioners to inject biases encoded in the structure of the input graph. Existing work in graph-based continuous control uses the physical morphology of the agent to construct the input graph, i.e., encoding limb features as node labels and using edges to connect the nodes if their corresponded limbs are physically connected. In this work, we present a series of ablations on existing methods that show that morphological information encoded in the graph does not improve their performance. Motivated by the hypothesis that any benefits GNNs extract from the graph structure are outweighed by difficulties they create for message passing, we also propose Amorpheus, a transformer-based approach. Further results show that, while Amorpheus ignores the morphological information that GNNs encode, it nonetheless substantially outperforms GNN-based methods.

READ FULL TEXT

page 7

page 15

09/17/2022

Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach

Graph Neural Networks (GNNs) are popular machine learning methods for mo...
02/18/2020

Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs

Graph neural networks (GNNs) have received much attention recently becau...
04/12/2021

Edgeless-GNN: Unsupervised Inductive Edgeless Network Embedding

We study the problem of embedding edgeless nodes such as users who newly...
04/21/2022

SoftEdge: Regularizing Graph Classification with Random Soft Edges

Graph data augmentation plays a vital role in regularizing Graph Neural ...
06/11/2021

Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns

Graph neural networks (GNNs) have achieved tremendous success on multipl...
09/20/2022

Neural Graph Databases

Graph databases (GDBs) enable processing and analysis of unstructured, c...
07/28/2021

Effective Eigendecomposition based Graph Adaptation for Heterophilic Networks

Graph Neural Networks (GNNs) exhibit excellent performance when graphs h...

Code Repositories