Skip to search boxSkip to navigationSkip to main content

Towards Interpretable Reinforcement Learning with Constrained Normalizing Flow Policies

Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
Peer-review

Open access

Publication Information

Output type

Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
Peer-review

Original language

English

Publication milestones

  • Published - 17/05/2024

Publication status

Published - 17/05/2024

Place of publication

Vienna, AT

Host publication title

Proceedings of the ICRA2024 Workshop on Human-aligned Reinforcement Learning for Autonomous Agents and Robots

Abstract

Reinforcement learning policies are typically represented by black-box neural networks, which are non-interpretable and not well-suited for safety-critical domains. To address both of these issues, we propose constrained normalizing flow policies as interpretable and safe-by-construction policy models. We achieve safety for reinforcement learning problems with instantaneous safety constraints, for which we can exploit domain knowledge by analytically constructing a normalizing flow that ensures constraint satisfaction. The normalizing flow corresponds to an interpretable sequence of transformations on action samples, each ensuring alignment with respect to a particular constraint. Our experiments reveal benefits beyond interpretability in an easier learning objective and maintained constraint satisfaction throughout the entire learning process. Our approach leverages constraints over reward engineering while offering enhanced interpretability, safety, and direct means of providing domain knowledge to the agent without relying on complex reward functions.

Access to documents

Related Event

Title

Workshop on Human-aligned Reinforcement Learning for Autonomous Agents and Robots

Event type

Workshop

Degree of recognition

International event

Date

17/05/2024

Location

YokohamaJapan