# Summarising and Comparing Agent Dynamics with Contrastive Spatiotemporal Abstraction

arXiv: https://arxiv.org/abs/2201.07749 · HTML: https://mlsanity.com/paper/2201.07749/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 17 Jan 2022.

## Builds on (most cited first, 9 of 9)

- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Verifiable Reinforcement Learning via Policy Extraction](https://mlsanity.com/paper/1805.08328/) (2018)
- [Graying the black box: Understanding DQNs](https://mlsanity.com/paper/1602.02658/) (2016)
- [Contrastive Explanation: A Structural-Model Approach](https://mlsanity.com/paper/1811.03163/) (2018)
- [Generation of Policy-Level Explanations for Reinforcement Learning](https://mlsanity.com/paper/1905.12044/) (2019)
- [Enabling Robots to Communicate their Objectives](https://mlsanity.com/paper/1702.03465/) (2017)
- [TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments](https://mlsanity.com/paper/2009.04743/) (2020)
- [Feature-Based Interpretable Reinforcement Learning based on State-Transition Models](https://mlsanity.com/paper/2105.07099/) (2021)

## Built on by (most cited first, 2 of 2)

- [Reward Learning with Trees: Methods and Evaluation](https://mlsanity.com/paper/2210.01007/) (2022)
- [Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2305.16924/) (2023)

## Abstract (arXiv)

We introduce a data-driven, model-agnostic technique for generating a human-interpretable summary of the salient points of contrast within an evolving dynamical system, such as the learning process of a control agent. It involves the aggregation of transition data along both spatial and temporal dimensions according to an information-theoretic divergence measure. A practical algorithm is outlined for continuous state spaces, and deployed to summarise the learning histories of deep reinforcement learning agents with the aid of graphical and textual communication methods. We expect our method to be complementary to existing techniques in the realm of agent interpretability.