SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.06178 · 2019

Curriculum Learning for Cumulative Return Maximization

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

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

Abstract

Curriculum learning has been successfully used in reinforcement learning to accelerate the learning process, through knowledge transfer between tasks of increasing complexity. Critical tasks, in which suboptimal exploratory actions must be minimized, can benefit from curriculum learning, and its ability to shape exploration through transfer. We propose a task sequencing algorithm maximizing the cumulative return, that is, the return obtained by the agent across all the learning episodes. By maximizing the cumulative return, the agent not only aims at achieving high rewards as fast as possible, but also at doing so while limiting suboptimal actions. We experimentally compare our task sequencing algorithm to several popular metaheuristic algorithms for combinatorial optimization, and show that it achieves significantly better performance on the problem of cumulative return maximization. Furthermore, we validate our algorithm on a critical task, optimizing a home controller for a micro energy grid.

For agents

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

get_harvested_code_for_paper("1906.06178")
get_code_for_paper("1906.06178")
have("1906.06178")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1906.06178.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1906.06178.svg)](https://syntology.ai/paper/1906.06178)

Connect an agent — have() is free.