Automating Curriculum Learning for Reinforcement Learning using a Skill-Based Bayesian Network
Year: 2025
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Hsiao, Vincent, Roberts, Mark, Hiatt, Laura M., Konidaris, George, Nau, Dana
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W6979301143
Cites:
Cited by:
Related to: