Safe Reinforcement Learning via Curriculum Induction
Matteo Turchetta, Andrey Kolobov, Shital Shah, Andreas Krause, Alekh, Agarwal

TL;DR
This paper introduces a curriculum induction method for safe reinforcement learning where an automatic instructor uses reset controllers to prevent dangerous actions, enabling safe and efficient learning without prior environment knowledge.
Contribution
It proposes a novel curriculum induction framework with a monitor and reset controllers, learning an optimal curriculum to enhance safety and learning efficiency in reinforcement learning.
Findings
Effective in two environments for safe learning
Reduces risk of damage during exploration
Improves learning speed and safety
Abstract
In safety-critical applications, autonomous agents may need to learn in an environment where mistakes can be very costly. In such settings, the agent needs to behave safely not only after but also while learning. To achieve this, existing safe reinforcement learning methods make an agent rely on priors that let it avoid dangerous situations during exploration with high probability, but both the probabilistic guarantees and the smoothness assumptions inherent in the priors are not viable in many scenarios of interest such as autonomous driving. This paper presents an alternative approach inspired by human teaching, where an agent learns under the supervision of an automatic instructor that saves the agent from violating constraints during learning. In this model, we introduce the monitor that neither needs to know how to do well at the task the agent is learning nor needs to know how the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsReinforcement Learning in Robotics · Adversarial Robustness in Machine Learning · Autonomous Vehicle Technology and Safety
MethodsSPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings
