I'm in Montréal to present new work on XAI for RL agents using World Models at the IJCAI Workshop on XAI, Aug 17 arxiv.org/abs/2505.08073
2
5
1
11
When an agent doesn't perform as expected, we run the world model backwards to generate counterfactual states from which the agent would have met expectations.

Aug 16, 2025 · 6:47 PM UTC

1
Explaining RL agent behaviors is wickedly hard. Even harder to provide non-technical end-users *actionable* insights. We show that our explanations are actionable, in that people can recognize what they need to do to get the desired behavior from an agent.
1
Also, we show that by telling users what they need to do to get desired behavior, we are helping users *control* the behavior of the agent through manipulation of the agent's environment. You can "program" an agent by manipulating its environment in just the right way.
1
This is work done by my amazing crew: Madhuri Singh, Amal Alabdulkarim, and Gennie Mansi.