mlsanityData to 7 Oct 2026

Learning from Demonstrations using Signal Temporal Logic

arXiv 2102.07730 ↗First posted 15 Feb 2021cs.RO cs.AI cs.LGcited by 17

On the map: Offline RL and imitation learning from data → Robot learning from demonstration

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.

Key facts. Cited by 17 papers in the map (data through 7 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.

Builds on

9 of 32 references.

References · 9

  1. 2016OpenAI Gymcited by 1,684
  2. 2018Behavioral Cloning from Observationcited by 482
  3. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  4. 2016Reinforcement Learning With Temporal Logic Rewardscited by 114
  5. 2016Q-Learning for Robust Satisfaction of Signal Temporal Logic Specificationscited by 65
  6. 2015Robust Online Monitoring of Signal Temporal Logiccited by 39
  7. 2017Interpretable Apprenticeship Learning with Temporal Logic Specificationscited by 13
  8. 2017Safety-Aware Apprenticeship Learningcited by 12
  9. 2018Automata Guided Reinforcement Learning With Demonstrationscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 2; 2024: 0; 2025: 2; 2026: 7.

17 papers.

Sort:

By area:

  1. 2025TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matchingcited by 9
  2. 2022Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxationcited by 8
  3. 2022Follow The Rules: Online Signal Temporal Logic Tree Search for Guided Imitation Learning in Stochastic Domainscited by 7
  4. 2023Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specificationscited by 6
  5. 2025TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Taskscited by 5
  6. 2021Back to Reality for Imitation Learningcited by 3
  7. 2022Learning Performance Graphs from Demonstrations via Task-Based Evaluationscited by 3
  8. 2022Quantification of Actual Road User Behavior on the Basis of Given Traffic Rulescited by 2
  9. 2022Interactive Learning from Natural Language and Demonstrations using Signal Temporal Logiccited by 2
  10. 2026RT-NeuS: Towards Real-Time Neuro-Symbolic Video Understanding via Adaptive Temporal Verificationcited by 2
  11. 2026Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specificationscited by 2
  12. 2023Signal Temporal Logic-Guided Apprenticeship Learningcited by 1
5 more
  1. 2026Learning Linear Temporal Specifications from Demonstrations with Uncertaintycited by 0
  2. 2026Logic-VLA: A Temporal Logic Conditioned Vision-Language-Action Modelcited by 0
  3. 2026Generalizable Multi-Agent Planning from Signal Temporal Logic Specifications via Diffusioncited by 0
  4. 2026From LLM-Generated Specifications to Learned Quadruped Locomotioncited by 0
  5. 2026Video2STL: Grounding VLM-Generated Temporal Specifications for Robot Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2020Elaborating on Learned Demonstrations with Temporal Logic Specifications
  2. 2019Maximum Causal Entropy Specification Inference from Demonstrations
  3. 2022Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations
  4. 2021Task-Guided Inverse Reinforcement Learning Under Partial Information
  5. 2025Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach
  6. 2023BC-IRL: Learning Generalizable Reward Functions from Demonstrations
  7. 2024Reward Machine Inference for Robotic Manipulation
  8. 2024Counter-example guided Imitation Learning of Feedback Controllers from Temporal Logic Specifications