Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing
arXiv:2103.01009
Abstract
Recent research has shown that graph neural networks (GNNs) can learn policies for locomotion control that are as effective as a typical multi-layer perceptron (MLP), with superior transfer and multi-task performance (Wang et al., 2018; Huang et al., 2020). Results have so far been limited to training on small agents, with the performance of GNNs deteriorating rapidly as the number of sensors and actuators grows. A key motivation for the use of GNNs in the supervised learning setting is their applicability to large graphs, but this benefit has not yet been realised for locomotion control. We identify the weakness with a common GNN architecture that causes this poor scaling: overfitting in the MLPs within the network that encode, decode, and propagate messages. To combat this, we introduce Snowflake, a GNN training method for high-dimensional continuous control that freezes parameters in parts of the network that suffer from overfitting. Snowflake significantly boosts the performance of GNNs for locomotion control on large agents, now matching the performance of MLPs, and with superior transfer properties.
20 pages, 14 figures, published at NeurIPS 2021
References in corpus (5)
- How transferable are features in deep neural networks?
- Emergence of Locomotion Behaviours in Rich Environments
- Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning
- Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs
- One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control