Beyond Value: C HECK L IST for Testing Inferences in Planning-Based RL

Reinforcement learning (RL) agents are commonly evaluated via their expected value over a distribution of test scenarios. Unfortunately, this evaluation approach provides limited evi- dence for post-deployment generalization beyond the test distribution. In this paper, we address this limitation by extend- ing the recent C HECK L IST testing methodology from natural language processing to planning-based RL. Specifically, we consider testing RL agents that make decisions via on-line tree search using a learned transition model and value function. The key idea is to improve the assessment of future performance via a C HECK L IST approach for exploring and assessing the agent’s inferences during tree search. The approach provides the user with an interface and general query- rule mechanism for identifying potential inference flaws and validating expected inference invariances. We present a user study involving knowledgeable AI researchers using the approach to evaluate an agent trained to play a complex real- time strategy game. The results show the approach is effective in allowing users to identify previously-unknown flaws in the agent’s reasoning. In addition, our analysis provides insight into how AI experts use this type of testing approach, which may help improve future instantiations.