Authors

* External authors

Venue

Date

Share

Proppo: a Message Passing Framework for Customizable and Composable Learning Algorithms

Paavo Parmas*

Takuma Seno

* External authors

NeurIPS 2022

2022

Abstract

While existing automatic differentiation (AD) frameworks allow flexibly composing model architectures, they do not provide the same flexibility for composing learning algorithms---everything has to be implemented in terms of back propagation. To address this gap, we invent Automatic Propagation (AP) software, which generalizes AD, and allows custom and composable construction of complex learning algorithms. The framework allows packaging custom learning algorithms into propagators that automatically implement the necessary computations, and can be reused across different computation graphs. We implement Proppo, a prototype AP software package built on top of the Pytorch AD framework. To demonstrate the utility of Proppo, we use it to implement Monte Carlo gradient estimation techniques, such as reparameterization and likelihood ratio gradients, as well as the total propagation algorithm and Gaussian shaping gradients, which were previously used in model-based reinforcement learning, but do not have any publicly available implementation. Finally, in minimalistic experiments, we show that these methods allow increasing the gradient accuracy by orders of magnitude, particularly when the machine learning system is at the edge of chaos.

Related Publications

SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning

ICLR, 2025
Hojoon Lee, Dongyoon Hwang, Donghu Kim, Hyunseung Kim, Jun Jet Tai, Kaushik Subramanian, Peter R. Wurman, Jaegul Choo, Peter Stone, Takuma Seno

Recent advances in CV and NLP have been largely driven by scaling up the number of network parameters, despite traditional theories suggesting that larger networks are prone to overfitting. These large networks avoid overfitting by integrating components that induce a simpli…

A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismo

RLC, 2024
Miguel Vasco*, Takuma Seno, Kenta Kawamoto, Kaushik Subramanian, Pete Wurman, Peter Stone

Racing autonomous cars faster than the best human drivers has been a longstanding grand challenge for the fields of Artificial Intelligence and robotics. Recently, an end-to-end deep reinforcement learning agent met this challenge in a high-fidelity racing simulator, Gran Tu…

Model-based Reinforcement Learning with Scalable Composite Policy Gradient Estimators

ICML, 2023
Paavo Parmas*, Takuma Seno, Yuma Aoki*

In model-based reinforcement learning (MBRL), policy gradients can be estimated either by derivative-free RL methods, such as likelihood ratio gradients (LR), or by backpropagating through a differentiable model via reparameterization gradients (RP). Instead of using one or …

  • HOME
  • Publications
  • Proppo: a Message Passing Framework for Customizable and Composable Learning Algorithms

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.