* External authors




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

Paavo Parmas*

Takuma Seno

* External authors

NeurIPS 2022



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

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 …

Value Function Decomposition for Iterative Design of Reinforcement Learning Agents

NeurIPS, 2022
James MacGlashan, Evan Archer, Alisa Devlic, Takuma Seno, Craig Sherstan, Peter R. Wurman, Peter Stone

Designing reinforcement learning (RL) agents is typically a difficult process that requires numerous design iterations. Learning can fail for a multitude of reasons and standard RL methods provide too few tools to provide insight into the exact cause. In this paper, we show …

d3rlpy: An Offline Deep Reinforcement Learning Library

Journal of Machine Learning Research, 2022
Takuma Seno, Michita Imai*

In this paper, we introduce d3rlpy, an open-sourced offline deep reinforcement learning (RL) library for Python. d3rlpy supports a set of offline deep RL algorithms as well as off-policy online algorithms via a fully documented plug-and-play API. To address a reproducibility…

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


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.