mlsanityData to 14 Oct 2026

One ACT Play: Single Demonstration Behavior Cloning with Action Chunking Transformers

arXiv 2309.10175 ↗First posted 18 Sep 2023cs.RO cs.AI cs.LGcited by 17

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

Abstract (arXiv)

Learning from human demonstrations (behavior cloning) is a cornerstone of robot learning. However, most behavior cloning algorithms require a large number of demonstrations to learn a task, especially for general tasks that have a large variety of initial conditions. Humans, however, can learn to complete tasks, even complex ones, after only seeing one or two demonstrations. Our work seeks to emulate this ability, using behavior cloning to learn a task given only a single human demonstration. We achieve this goal by using linear transforms to augment the single demonstration, generating a set of trajectories for a wide range of initial conditions. With these demonstrations, we are able to train a behavior cloning agent to successfully complete three block manipulation tasks. Additionally, we developed a novel addition to the temporal ensembling method used by action chunking agents during inference. By incorporating the standard deviation of the action predictions into the ensembling method, our approach is more robust to unforeseen changes in the environment, resulting in significant performance improvements.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 19 of its 38 references that are in the map. First posted on arXiv 18 Sep 2023.

Builds on

19 of 38 references.

Closest ancestors · 2

Same direction, newest first

  1. 2021On the Sample Complexity of Stability Constrained Imitation Learning18 Feb
  2. 2018Behavioral Cloning from Observation4 May

Other references · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  4. 2016End to End Learning for Self-Driving Carscited by 1,009
  5. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 725
  6. 2017Overcoming Exploration in Reinforcement Learning with Demonstrationscited by 340
  7. 2022Behavior Transformers: Cloning k modes with one stonecited by 304
  8. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 289
  9. 2017Reverse Curriculum Generation for Reinforcement Learningcited by 198
  10. 2023RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunkingcited by 169
  11. 2018Learning Montezuma's Revenge from a Single Demonstrationcited by 80
  12. 2023Diffusion Model-Augmented Behavioral Cloningcited by 38
5 more
  1. 2022Back to the Manifold: Recovering from Out-of-Distribution Statescited by 20
  2. 2023OpenVR: Teleoperation for Manipulationcited by 8
  3. 2022Minimizing Human Assistance: Augmenting a Single Demonstration for Deep Reinforcement Learningcited by 5
  4. 2023RoboChop: Autonomous Framework for Fruit and Vegetable Chopping Leveraging Foundational Modelscited by 5
  5. 2019Creativity in Robot Manipulation with Deep Reinforcement Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 5; 2026: 5.

17 papers.

Sort:

By area:

  1. 2025Real-Time Execution of Action Chunking Flow Policiescited by 216
  2. 2025Reinforcement Learning with Action Chunkingcited by 107
  3. 2024Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Samplingcited by 52
  4. 2024Bi-ACT: Bilateral Control-Based Imitation Learning via Action Chunking with Transformercited by 27
  5. 2024VITaL Pretraining: Visuo-Tactile Pretraining for Tactile and Non-Tactile Manipulation Policiescited by 15
  6. 2024SculptDiff: Learning Robotic Clay Sculpting from Humans with Goal Conditioned Diffusion Policycited by 7
  7. 2025RT-Cache: Training-Free Retrieval for Real-Time Manipulationcited by 6
  8. 2026StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observationcited by 6
  9. 2024ARCADE: Scalable Demonstration Collection and Generation via Augmented Reality for Imitation Learningcited by 5
  10. 2026Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policycited by 3
  11. 2024Subconscious Robotic Imitation Learningcited by 2
  12. 2024ALPHA-α and Bi-ACT Are All You Need: Importance of Position and Force Information/Control for Imitation Learning of Unimanual and Bimanual Robotic Manipulation with Low-Cost Systemcited by 1
5 more
  1. 2025What Do You Need for Compositional Generalization in Diffusion Planning?cited by 0
  2. 2025One-shot Adaptation of Humanoid Whole-body Motion with Walking Priorscited by 0
  3. 2026Expert Behavior Prior Reinforcement Learningcited by 0
  4. 2026Improving Online Reinforcement Learning via Bidirectional Behavior Prior Distillationcited by 0
  5. 2026REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025CLASS: Contrastive Learning via Action Sequence Supervision for Robot Manipulation
  2. 2020Concurrent Training Improves the Performance of Behavioral Cloning from Observation
  3. 2025Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control
  4. 2025R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations
  5. 2025Counterfactual Behavior Cloning: Offline Imitation Learning from Imperfect Human Demonstrations
  6. 2020Imitating Unknown Policies via Exploration
  7. 2025Learning a Thousand Tasks in a Day
  8. 2025Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking