Saved in:
Bibliographic Details
Main Authors: Hsiao, Vincent, Roberts, Mark, Hiatt, Laura M., Konidaris, George, Nau, Dana
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.15662
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910839191109632
author Hsiao, Vincent
Roberts, Mark
Hiatt, Laura M.
Konidaris, George
Nau, Dana
author_facet Hsiao, Vincent
Roberts, Mark
Hiatt, Laura M.
Konidaris, George
Nau, Dana
contents A major challenge for reinforcement learning is automatically generating curricula to reduce training time or improve performance in some target task. We introduce SEBNs (Skill-Environment Bayesian Networks) which model a probabilistic relationship between a set of skills, a set of goals that relate to the reward structure, and a set of environment features to predict policy performance on (possibly unseen) tasks. We develop an algorithm that uses the inferred estimates of agent success from SEBN to weigh the possible next tasks by expected improvement. We evaluate the benefit of the resulting curriculum on three environments: a discrete gridworld, continuous control, and simulated robotics. The results show that curricula constructed using SEBN frequently outperform other baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2502_15662
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automating Curriculum Learning for Reinforcement Learning using a Skill-Based Bayesian Network
Hsiao, Vincent
Roberts, Mark
Hiatt, Laura M.
Konidaris, George
Nau, Dana
Artificial Intelligence
Machine Learning
A major challenge for reinforcement learning is automatically generating curricula to reduce training time or improve performance in some target task. We introduce SEBNs (Skill-Environment Bayesian Networks) which model a probabilistic relationship between a set of skills, a set of goals that relate to the reward structure, and a set of environment features to predict policy performance on (possibly unseen) tasks. We develop an algorithm that uses the inferred estimates of agent success from SEBN to weigh the possible next tasks by expected improvement. We evaluate the benefit of the resulting curriculum on three environments: a discrete gridworld, continuous control, and simulated robotics. The results show that curricula constructed using SEBN frequently outperform other baselines.
title Automating Curriculum Learning for Reinforcement Learning using a Skill-Based Bayesian Network
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2502.15662