# Explaining Conditions for Reinforcement Learning Behaviors from Real and Imagined Data

arXiv: https://arxiv.org/abs/2011.09004 · HTML: https://mlsanity.com/paper/2011.09004/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2020.

## Built on by (most cited first, 3 of 3)

- [Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey](https://mlsanity.com/paper/2108.09003/) (2021)
- [Competency Assessment for Autonomous Agents using Deep Generative Models](https://mlsanity.com/paper/2203.12670/) (2022)
- [Symmetry Detection in Trajectory Data for More Meaningful Reinforcement Learning Representations](https://mlsanity.com/paper/2211.16381/) (2022)

## Abstract (arXiv)

The deployment of reinforcement learning (RL) in the real world comes with challenges in calibrating user trust and expectations. As a step toward developing RL systems that are able to communicate their competencies, we present a method of generating human-interpretable abstract behavior models that identify the experiential conditions leading to different task execution strategies and outcomes. Our approach consists of extracting experiential features from state representations, abstracting strategy descriptors from trajectories, and training an interpretable decision tree that identifies the conditions most predictive of different RL behaviors. We demonstrate our method on trajectory data generated from interactions with the environment and on imagined trajectory data that comes from a trained probabilistic world model in a model-based RL setting.