IxDRL: A Novel Explainable Deep Reinforcement Learning Toolkit Based on Analyses of Interestingness

Sequeira, Pedro; Gervasio, Melinda

doi:10.1007/978-3-031-44064-9_20

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2024

Publication Types

Select...

Book1

Article1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Exploring the Reliability of SHAP Values in Reinforcement Learning

Engelhardt,

Lange,

Wiskott

et al. 2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Exploring the Reliability of SHAP Values in Reinforcement Learning

Engelhardt,

Lange,

Wiskott

et al. 2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Automated gadget discovery in the quantum domain

Trenkwalder,

López-Incera,

Poulsen Nautrup

et al. 2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

In recent years, reinforcement learning (RL) has become increasingly successful in its application to the quantum domain and the process of scientific discovery in general. However, while RL algorithms learn to solve increasingly complex problems, interpreting the solutions they provide becomes ever more challenging. In this work, we gain insights into an RL agent’s learned behavior through a post-hoc analysis based on sequence mining and clustering. Specifically, frequent and compact subroutines, used by the agent to solve a given task, are distilled as gadgets and then grouped by various metrics. This process of gadget discovery develops in three stages: First, we use an RL agent to generate data, then, we employ a mining algorithm to extract gadgets and finally, the obtained gadgets are grouped by a density-based clustering algorithm. We demonstrate our method by applying it to two quantum-inspired RL environments. First, we consider simulated quantum optics experiments for the design of high-dimensional multipartite entangled states where the algorithm finds gadgets that correspond to modern interferometer setups. Second, we consider a circuit-based quantum computing environment where the algorithm discovers various gadgets for quantum information processing, such as quantum teleportation. This approach for analyzing the policy of a learned agent is agent and environment agnostic and can yield interesting insights into any agent’s policy.

show abstract

IxDRL: A Novel Explainable Deep Reinforcement Learning Toolkit Based on Analyses of Interestingness

Cited by 2 publications

References 33 publications

Exploring the Reliability of SHAP Values in Reinforcement Learning

Exploring the Reliability of SHAP Values in Reinforcement Learning

Automated gadget discovery in the quantum domain

Contact Info

Product

Resources

About