Interactive Visualization for Debugging RL
Shuby Deshpande, Benjamin Eysenbach, Jeff Schneider

TL;DR
This paper introduces an interactive visualization tool tailored for debugging and interpreting reinforcement learning algorithms, addressing unique challenges not covered by existing supervised learning visualization tools.
Contribution
The work presents a novel interactive visualization system specifically designed for RL debugging, incorporating features like different state representations and a flexible framework.
Findings
Enhanced understanding of RL policies through visualization
Facilitated debugging process for RL algorithms
Framework adaptable for future extensions
Abstract
Visualization tools for supervised learning allow users to interpret, introspect, and gain an intuition for the successes and failures of their models. While reinforcement learning practitioners ask many of the same questions, existing tools are not applicable to the RL setting as these tools address challenges typically found in the supervised learning regime. In this work, we design and implement an interactive visualization tool for debugging and interpreting RL algorithms. Our system addresses many features missing from previous tools such as (1) tools for supervised learning often are not interactive; (2) while debugging RL policies researchers use state representations that are different from those seen by the agent; (3) a framework designed to make the debugging RL policies more conducive. We provide an example workflow of how this system could be used, along with ideas for…
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.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsReinforcement Learning in Robotics · Software Engineering Research · Sports Analytics and Performance
