# Learning from Demonstrations using Signal Temporal Logic

arXiv: https://arxiv.org/abs/2102.07730 · HTML: https://mlsanity.com/paper/2102.07730/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Robot learning from demonstration, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 9 of its 32 references that are in the map.
- First posted on arXiv 15 Feb 2021.

## Placed in

- Offline RL and imitation learning from data / [Robot learning from demonstration](https://mlsanity.com/offlinerl/robot-learning-from-demonstration/)

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

- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Reinforcement Learning With Temporal Logic Rewards](https://mlsanity.com/paper/1612.03471/) (2016)
- [Q-Learning for Robust Satisfaction of Signal Temporal Logic Specifications](https://mlsanity.com/paper/1609.07409/) (2016)
- [Robust Online Monitoring of Signal Temporal Logic](https://mlsanity.com/paper/1506.08234/) (2015)
- [Interpretable Apprenticeship Learning with Temporal Logic Specifications](https://mlsanity.com/paper/1710.10532/) (2017)
- [Safety-Aware Apprenticeship Learning](https://mlsanity.com/paper/1710.07983/) (2017)
- [Automata Guided Reinforcement Learning With Demonstrations](https://mlsanity.com/paper/1809.06305/) (2018)

## Built on by (most cited first, 17 of 17)

- [TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching](https://mlsanity.com/paper/2505.00562/) (2025)
- [Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxation](https://mlsanity.com/paper/2201.08504/) (2022)
- [Follow The Rules: Online Signal Temporal Logic Tree Search for Guided Imitation Learning in Stochastic Domains](https://mlsanity.com/paper/2209.13737/) (2022)
- [Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications](https://mlsanity.com/paper/2306.06808/) (2023)
- [TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks](https://mlsanity.com/paper/2510.00225/) (2025)
- [Back to Reality for Imitation Learning](https://mlsanity.com/paper/2111.12867/) (2021)
- [Learning Performance Graphs from Demonstrations via Task-Based Evaluations](https://mlsanity.com/paper/2204.05909/) (2022)
- [Quantification of Actual Road User Behavior on the Basis of Given Traffic Rules](https://mlsanity.com/paper/2202.09269/) (2022)
- [Interactive Learning from Natural Language and Demonstrations using Signal Temporal Logic](https://mlsanity.com/paper/2207.00627/) (2022)
- [RT-NeuS: Towards Real-Time Neuro-Symbolic Video Understanding via Adaptive Temporal Verification](https://mlsanity.com/paper/2602.23553/) (2026)
- [Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications](https://mlsanity.com/paper/2607.00442/) (2026)
- [Signal Temporal Logic-Guided Apprenticeship Learning](https://mlsanity.com/paper/2311.05084/) (2023)
- [Learning Linear Temporal Specifications from Demonstrations with Uncertainty](https://mlsanity.com/paper/2607.10918/) (2026)
- [Logic-VLA: A Temporal Logic Conditioned Vision-Language-Action Model](https://mlsanity.com/paper/2608.20556/) (2026)
- [Generalizable Multi-Agent Planning from Signal Temporal Logic Specifications via Diffusion](https://mlsanity.com/paper/2608.29490/) (2026)
- [From LLM-Generated Specifications to Learned Quadruped Locomotion](https://mlsanity.com/paper/2609.07111/) (2026)
- [Video2STL: Grounding VLM-Generated Temporal Specifications for Robot Learning](https://mlsanity.com/paper/2609.37519/) (2026)

## Abstract (arXiv)

Learning-from-demonstrations is an emerging paradigm to obtain effective robot control policies for complex tasks via reinforcement learning without the need to explicitly design reward functions. However, it is susceptible to imperfections in demonstrations and also raises concerns of safety and interpretability in the learned control policies. To address these issues, we use Signal Temporal Logic to evaluate and rank the quality of demonstrations. Temporal logic-based specifications allow us to create non-Markovian rewards, and also define interesting causal dependencies between tasks such as sequential task specifications. We validate our approach through experiments on discrete-world and OpenAI Gym environments, and show that our approach outperforms the state-of-the-art Maximum Causal Entropy Inverse Reinforcement Learning.