Interactive Visualization for Debugging RL
This work addresses a practical problem for RL practitioners by providing a tool to improve debugging and interpretation, but it is incremental as it builds on existing visualization concepts for a specific domain.
The paper tackles the lack of interactive visualization tools for debugging reinforcement learning (RL) algorithms by designing and implementing a new system that addresses specific gaps, such as non-interactivity and mismatched state representations, compared to existing supervised learning tools.
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 future extensions.