Learning from Successful and Failed Demonstrations via Optimization
On the map: Offline RL and imitation learning from data → Robot learning from demonstration
Abstract (arXiv)
Learning from Demonstration (LfD) is a popular approach that allows humans to teach robots new skills by showing the correct way(s) of performing the desired skill. Human-provided demonstrations, however, are not always optimal and the teacher usually addresses this issue by discarding or replacing sub-optimal (noisy or faulty) demonstrations. We propose a novel LfD representation that learns from both successful and failed demonstrations of a skill. Our approach encodes the two subsets of captured demonstrations (labeled by the teacher) into a statistical skill model, constructs a set of quadratic costs, and finds an optimal reproduction of the skill under novel problem conditions (i.e. constraints). The optimal reproduction balances convergence towards successful examples and divergence from failed examples. We evaluate our approach through several 2D and 3D experiments in real-world using a UR5e manipulator arm and also show that it can reproduce a skill from only failed demonstrations. The benefits of exploiting both failed and successful demonstrations are shown through comparison with two existing LfD approaches. We also compare our approach against an existing skill refinement method and show its capabilities in a multi-coordinate setting.
Key facts. Cited by 3 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. First posted on arXiv 26 Jul 2021.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 1; 2023: 0; 2024: 0; 2025: 0; 2026: 1.
3 papers.
- 2021Similarity-Aware Skill Reproduction based on Multi-Representational Learning from Demonstrationcited by 2
- 2022Robot Learning from Demonstration Using Elastic Mapscited by 1
- 2026How to Utilize Failure Demo Data?: Effective Data Selection for Imitation Learning Using Distribution Differences in Attention Mechanismcited by 0
- 2026How to Utilize Failure Demo Data?: Effective Data Selection for Imitation Learning Using Distribution Differences in Attention Mechanism8 May 2026
- 2022Robot Learning from Demonstration Using Elastic Maps3 Aug 2022
- 2021Similarity-Aware Skill Reproduction based on Multi-Representational Learning from Demonstration28 Oct 2021
Similar, not cited
Close in wording, no citation either way
- 2018Learning Generalizable Robot Skills from Demonstrations in Cluttered Environments
- 2023Learning from Few Demonstrations with Frame-Weighted Motion Generation
- 2020Learning from Suboptimal Demonstration via Self-Supervised Reward Regression
- 2022Quantifying Demonstration Quality for Robot Learning and Generalization
- 2024Consistency Matters: Defining Demonstration Data Quality Metrics in Robot Learning from Demonstration
- 2025Demonstration Sidetracks: Categorizing Systematic Non-Optimality in Human Demonstrations
- 2021Ergodic imitation: Learning from what to do and what not to do
- 2025When a Robot is More Capable than a Human: Learning from Constrained Demonstrators