Interpretable Imitation Learning via Generative Adversarial STL Inference and Control
On the map: Offline RL and imitation learning from data → Imitation learning methods
Abstract (arXiv)
Imitation learning methods have demonstrated considerable success in teaching autonomous systems complex tasks through expert demonstrations. However, a limitation of these methods is their lack of interpretability, particularly in understanding the specific task the learning agent aims to accomplish. In this paper, we propose a novel imitation learning method that combines Signal Temporal Logic (STL) inference and control synthesis, enabling the explicit representation of the task as an STL formula. This approach not only provides a clear understanding of the task but also supports the integration of human knowledge and allows for adaptation to out-of-distribution scenarios by manually adjusting the STL formulas and fine-tuning the policy. We employ a Generative Adversarial Network (GAN)-inspired approach to train both the inference and policy networks, effectively narrowing the gap between expert and learned policies. The efficiency of our algorithm is demonstrated through simulations, showcasing its practical applicability and adaptability.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 17 of its 41 references that are in the map. First posted on arXiv 15 Feb 2024.
Builds on
17 of 41 references.
References · 17
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
- 2016OpenAI Gymcited by 1,684
- 2016Generative Adversarial Imitation Learningcited by 1,576
- 2017Robust Imitation of Diverse Behaviorscited by 85
- 2016Q-Learning for Robust Satisfaction of Signal Temporal Logic Specificationscited by 65
- 2015Robust Temporal Logic Model Predictive Controlcited by 21
- 2020A Smooth Robustness Measure of Signal Temporal Logic for Symbolic Controlcited by 21
- 2019Interpretable Classification of Time-Series Data using Efficient Enumerative Techniquescited by 19
- 2020Recurrent Neural Network Controllers for Signal Temporal Logic Specifications Subject to Safety Constraintscited by 18
- 2015Mining Parametric Temporal Logic Properties in Model Based Design for Cyber-Physical Systemscited by 16
- 2019Control from Signal Temporal Logic Specifications with Smooth Cumulative Quantitative Semanticscited by 16
5 more
- 2022Semi-Supervised Trajectory-Feedback Controller Synthesis for Signal Temporal Logic Specificationscited by 11
- 2022Learning Signal Temporal Logic through Neural Network for Interpretable Classificationcited by 10
- 2021Classification of Time-Series Data Using Boosted Decision Treescited by 9
- 2022Interpretable Fault Diagnosis of Rolling Element Bearings with Temporal Logic Neural Networkcited by 4
- 2021Safe Model-based Control from Signal Temporal Logic Specifications Using Recurrent Neural Networkscited by 3
Built on by
Citing papers per year: 2024: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2022Follow The Rules: Online Signal Temporal Logic Tree Search for Guided Imitation Learning in Stochastic Domains
- 2018Learning Temporal Strategic Relationships using Generative Adversarial Imitation Learning
- 2019Hindsight Generative Adversarial Imitation Learning
- 2025SD2AIL: Adversarial Imitation Learning from Synthetic Demonstrations via Diffusion Models
- 2022Latent Policies for Adversarial Imitation Learning
- 2018Sample-Efficient Imitation Learning via Generative Adversarial Nets
- 2018Generative Adversarial Imitation from Observation
- 2020ADAIL: Adaptive Adversarial Imitation Learning