OpenAI Blog
Mar 21, 2017
Third-person imitation learning
Related stories
arXiv Machine Learning
Aug 3
Mirror Learning
arXiv:2607. 28737v1 Announce Type: new Abstract: We investigate imitation learning through the lens of third-person observation and propose a framework for mirror learning: acquiring actionable policies from passive observation.
arXiv AI
Jun 19
Human-like autonomy emerges from self-play and a pinch of human data
arXiv:2606. 19370v1 Announce Type: cross Abstract: Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data.
arXiv Machine Learning
Jul 31
Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach
arXiv:2605. 07166v2 Announce Type: replace Abstract: Imitation learning is widely used for learning to act in complex environments.
arXiv AI
Jun 9
Difference-Aware Retrieval Policies for Imitation Learning
arXiv:2606. 09758v1 Announce Type: cross Abstract: Parametric imitation learning via behavior cloning can suffer from poor generalization to out-of-distribution states due to compounding errors during deployment.
arXiv AI
Jun 18
R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations
arXiv:2510. 18085v2 Announce Type: replace-cross Abstract: Imitation Learning (IL) is a natural way for humans to teach robots, particularly when high-quality demonstrations are easy to obtain.
arXiv Machine Learning
Jun 16
DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy
arXiv:2506. 20668v3 Announce Type: replace-cross Abstract: We propose DemoDiffusion, a simple method for enabling robots to perform manipulation tasks by imitating a single human demonstration, without requiring task-specific training or paired human-robot data.
arXiv Machine Learning
4d ago
BlenDAgger: Blended Shared Control for Interactive Imitation Learning
arXiv:2609.37599v1 Announce Type: cross Abstract: Robot policies are frequently trained from human corrections, yet teleoperating a robot to provide corrections is burdensome, and human demonstrators...
arXiv Computer Vision
Sep 1
RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion
arXiv:2512.23649v5 Announce Type: replace-cross Abstract: Humans learn locomotion through visual observation, interpreting visual content first before imitating actions. However, state-of-the-art hum...
arXiv AI
Jun 11
Noise-Guided Transport for Imitation Learning
arXiv:2509. 26294v2 Announce Type: replace-cross Abstract: We consider imitation learning in the low-data regime, where only a limited number of expert demonstrations are available.
Hugging Face Trending Papers
Aug 24
Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulation
Ensuring reliability in uncertain environments remains difficult for long-horizon robotic manipulation. End-to-end VLA models are data-heavy and opaque, making diagnosis and verification difficult. Hi...
arXiv AI
Aug 25
Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulation
Triplet2Track (TTS) is a closed‑loop long‑horizon imitation learning system that uses human videos to reduce robot‑collected data. It represents high‑level subgoals as instance‑grounded triplets, converts them into continuous track priors for execution, and monitors task progress from observations for online replanning. In diverse real‑world long‑horizon tasks, TTS achieves a 74.8% average success rate and supports object‑level and compositional generalization.