SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.04836 · ICLR · 2022

Deconstructing the Inductive Biases of Hamiltonian Neural Networks

Marc Finzi, Samuel Stanton, Andrew Wilson, Nate Gruver

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
ngruver/decon-hnn canonical 1 of 1
copy not recorded — 1 of 1
FunctionStatusWhere it lives
count_parameters Ran this paper's copy was not recorded; identical code first harvested from crisbodnar/ndp
pointer only · get_code("f6b944f50d3f15ae")
seq_rmse Ran ngruver/decon-hnn/mujoco.py
code served (permissive licence) · get_code("3aedf2ead3965763")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Physics-inspired neural networks (NNs), such as Hamiltonian or Lagrangian NNs, dramatically outperform other learned dynamics models by leveraging strong inductive biases. These models, however, are challenging to apply to many real world systems, such as those that don't conserve energy or contain contacts, a common setting for robotics and reinforcement learning. In this paper, we examine the inductive biases that make physics-inspired models successful in practice. We show that, contrary to conventional wisdom, the improved generalization of HNNs is the result of modeling acceleration directly and avoiding artificial complexity from the coordinate system, rather than symplectic structure or energy conservation. We show that by relaxing the inductive biases of these models, we can match or exceed performance on energy-conserving systems while dramatically improving performance on practical, non-conservative systems. We extend this approach to constructing transition models for common Mujoco environments, showing that our model can appropriately balance inductive biases with the flexibility required for model-based control.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2202.04836")
get_code_for_paper("2202.04836")
have("2202.04836")

Connect an agent — have() is free.