# Imitation Learning from a Single Temporally Misaligned Video

arXiv: https://arxiv.org/abs/2502.05397 · HTML: https://mlsanity.com/paper/2502.05397/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 34 of its 42 references that are in the map.
- First posted on arXiv 8 Feb 2025.

## Placed in

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

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification](https://mlsanity.com/paper/1712.04851/) (2017)
- [Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning](https://mlsanity.com/paper/2107.09645/) (2021)
- [One-Shot Imitation Learning](https://mlsanity.com/paper/1703.07326/) (2017)
- [LIV: Language-Image Representations and Rewards for Robotic Control](https://mlsanity.com/paper/2306.00958/) (2023)
- [Generative Adversarial Imitation from Observation](https://mlsanity.com/paper/1807.06158/) (2018)
- [Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning](https://mlsanity.com/paper/2310.12921/) (2023)
- [Prompting Decision Transformer for Few-Shot Policy Generalization](https://mlsanity.com/paper/2206.13499/) (2022)
- [RoboCLIP: One Demonstration is Enough to Learn Robot Policies](https://mlsanity.com/paper/2310.07899/) (2023)
- [Primal Wasserstein Imitation Learning](https://mlsanity.com/paper/2006.04678/) (2020)
- [Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap](https://mlsanity.com/paper/2103.03236/) (2021)
- [Provably Efficient Imitation Learning from Observation Alone](https://mlsanity.com/paper/1905.10948/) (2019)
- [Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations](https://mlsanity.com/paper/2303.01497/) (2023)
- [Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics](https://mlsanity.com/paper/2403.19578/) (2024)
- [Watch and Match: Supercharging Imitation with Regularized Optimal Transport](https://mlsanity.com/paper/2206.15469/) (2022)
- [Wasserstein Adversarial Imitation Learning](https://mlsanity.com/paper/1906.08113/) (2019)
- [Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers](https://mlsanity.com/paper/2403.12943/) (2024)
- [Fast Traversability Estimation for Wild Visual Navigation](https://mlsanity.com/paper/2305.08510/) (2023)
- [Optimal Transport for Offline Imitation Learning](https://mlsanity.com/paper/2303.13971/) (2023)
- [See to Touch: Learning Tactile Dexterity through Visual Incentives](https://mlsanity.com/paper/2309.12300/) (2023)
- [Rank2Reward: Learning Shaped Reward Functions from Passive Video](https://mlsanity.com/paper/2404.14735/) (2024)
- [Imitation Learning with Sinkhorn Distances](https://mlsanity.com/paper/2008.09167/) (2020)
- [FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning](https://mlsanity.com/paper/2406.00645/) (2024)
- [For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal](https://mlsanity.com/paper/2304.04591/) (2023)
- [What Matters to You? Towards Visual Representation Alignment for Robot Learning](https://mlsanity.com/paper/2310.07932/) (2023)

## Built on by (most cited first, 7 of 7)

- [TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance](https://mlsanity.com/paper/2509.26627/) (2025)
- [X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations](https://mlsanity.com/paper/2511.04671/) (2025)
- [Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience](https://mlsanity.com/paper/2606.27475/) (2026)
- [Minimal Ingredients for Reward Assignment from Expert Demonstrations](https://mlsanity.com/paper/2506.06793/) (2025)
- [Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoning](https://mlsanity.com/paper/2603.18495/) (2026)
- [FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy](https://mlsanity.com/paper/2605.15944/) (2026)
- [Rank-Then-Act: Reward-Free Control from Frame-Order Progress](https://mlsanity.com/paper/2607.01897/) (2026)

## Abstract (arXiv)

We examine the problem of learning sequential tasks from a single visual demonstration. A key challenge arises when demonstrations are temporally misaligned due to variations in timing, differences in embodiment, or inconsistencies in execution. Existing approaches treat imitation as a distribution-matching problem, aligning individual frames between the agent and the demonstration. However, we show that such frame-level matching fails to enforce temporal ordering or ensure consistent progress. Our key insight is that matching should instead be defined at the level of sequences. We propose that perfect matching occurs when one sequence successfully covers all the subgoals in the same order as the other sequence. We present ORCA (ORdered Coverage Alignment), a dense per-timestep reward function that measures the probability of the agent covering demonstration frames in the correct order. On temporally misaligned demonstrations, we show that agents trained with the ORCA reward achieve 4.5x improvement (0.11 rightarrow 0.50 average normalized returns) for Meta-world tasks and 6.6x improvement (6.55 rightarrow 43.3 average returns) for Humanoid-v4 tasks compared to the best frame-level matching algorithms. We also provide empirical analysis showing that ORCA is robust to varying levels of temporal misalignment. Our code is available at https://github.com/portal-cornell/orca/