Vizarel: A System to Help Better Understand RL Agents
This work addresses the problem of interpretability in RL for practitioners, but it is incremental as it presents an initial prototype without demonstrated impact.
The paper tackles the lack of visualization tools for reinforcement learning (RL) agents by proposing Vizarel, a prototype system designed to help users understand RL models through interpretable features, but it does not report concrete results or numbers.
Visualization tools for supervised learning have allowed users to interpret, introspect, and gain 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. In this work, we describe our initial attempt at constructing a prototype of these ideas, through identifying possible features that such a system should encapsulate. Our design is motivated by envisioning the system to be a platform on which to experiment with interpretable reinforcement learning.