mlsanityData to 7 Oct 2026

To Follow or not to Follow: Selective Imitation Learning from Observations

arXiv 1912.07670 ↗First posted 16 Dec 2019cs.RO cs.AI cs.LGcited by 10

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Learning from demonstrations is a useful way to transfer a skill from one agent to another. While most imitation learning methods aim to mimic an expert skill by following the demonstration step-by-step, imitating every step in the demonstration often becomes infeasible when the learner and its environment are different from the demonstration. In this paper, we propose a method that can imitate a demonstration composed solely of observations, which may not be reproducible with the current agent. Our method, dubbed selective imitation learning from observations (SILO), selects reachable states in the demonstration and learns how to reach the selected states. Our experiments on both simulated and real robot environments show that our method reliably performs a new task by following a demonstration. Videos and code are available at https://clvrai.com/silo .

Key facts. Cited by 10 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 22 of its 33 references that are in the map. First posted on arXiv 16 Dec 2019.

Builds on

22 of 33 references.

References · 22

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  4. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  5. 2017Hindsight Experience Replaycited by 1,096
  6. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
  7. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
  8. 2015Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Imagescited by 266
  9. 2017One-Shot Imitation Learningcited by 232
  10. 2017One-Shot Visual Imitation Learning via Meta-Learningcited by 225
  11. 2017Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translationcited by 167
  12. 2015Deep Spatial Autoencoders for Visuomotor Learningcited by 149
10 more
  1. 2018One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learningcited by 146
  2. 2019End-to-End Robotic Reinforcement Learning without Reward Engineeringcited by 115
  3. 2018Zero-Shot Visual Imitationcited by 114
  4. 2017Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulationcited by 90
  5. 2017Neural Task Programming: Learning to Generalize Across Hierarchical Taskscited by 75
  6. 2019IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Taskscited by 68
  7. 2016Unsupervised Perceptual Rewards for Imitation Learningcited by 64
  8. 2018One-Shot Hierarchical Imitation Learning of Compound Visuomotor Taskscited by 32
  9. 2018Universal Planning Networkscited by 29
  10. 2019Unsupervised Visuomotor Control through Distributional Planning Networkscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 2; 2021: 2; 2022: 2; 2023: 1; 2024: 0; 2025: 1; 2026: 2.

10 papers.

  1. 2023FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulationcited by 132
  2. 2021Learning to Synthesize Programs as Interpretable and Generalizable Policiescited by 59
  3. 2020Domain-Adversarial and Conditional State Space Model for Imitation Learningcited by 7
  4. 2022Abstract-to-Executable Trajectory Translation for One-Shot Task Generalizationcited by 2
  5. 2020HILONet: Hierarchical Imitation Learning from Non-Aligned Observationscited by 1
  6. 2021Introspective Visuomotor Control: Exploiting Uncertainty in Deep Visuomotor Control for Failure Recoverycited by 1
  7. 2022Case-Based Inverse Reinforcement Learning Using Temporal Coherencecited by 1
  8. 2026Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videoscited by 1
  9. 2025Learning from Observation: A Survey of Recent Advancescited by 0
  10. 2026SynthICL: Scalable In-context Imitation Learning with Synthetic Datacited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Explorative Imitation Learning: A Path Signature Approach for Continuous Environments
  2. 2021Learning from Imperfect Demonstrations from Agents with Varying Dynamics
  3. 2024A Dual Approach to Imitation Learning from Observations with Offline Datasets
  4. 2026Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift
  5. 2021Learning Multi-Stage Tasks with One Demonstration via Self-Replay
  6. 2023Imitation Learning from Observation with Automatic Discount Scheduling
  7. 2019Watch, Try, Learn: Meta-Learning from Demonstrations and Reward
  8. 2022Robust Learning from Observation with Model Misspecification