In-Context Imitation Learning via Next-Token Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929519244345344 |
|---|---|
| author | Fu, Letian Huang, Huang Datta, Gaurav Chen, Lawrence Yunliang Panitch, William Chung-Ho Liu, Fangchen Li, Hui Goldberg, Ken |
| author_facet | Fu, Letian Huang, Huang Datta, Gaurav Chen, Lawrence Yunliang Panitch, William Chung-Ho Liu, Fangchen Li, Hui Goldberg, Ken |
| contents | We explore how to enhance next-token prediction models to perform in-context imitation learning on a real robot, where the robot executes new tasks by interpreting contextual information provided during the input phase, without updating its underlying policy parameters. We propose In-Context Robot Transformer (ICRT), a causal transformer that performs autoregressive prediction on sensorimotor trajectories without relying on any linguistic data or reward function. This formulation enables flexible and training-free execution of new tasks at test time, achieved by prompting the model with sensorimotor trajectories of the new task composing of image observations, actions and states tuples, collected through human teleoperation. Experiments with a Franka Emika robot demonstrate that the ICRT can adapt to new tasks specified by prompts, even in environment configurations that differ from both the prompt and the training data. In a multitask environment setup, ICRT significantly outperforms current state-of-the-art next-token prediction models in robotics on generalizing to unseen tasks. Code, checkpoints and data are available on https://icrt.dev/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_15980 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | In-Context Imitation Learning via Next-Token Prediction Fu, Letian Huang, Huang Datta, Gaurav Chen, Lawrence Yunliang Panitch, William Chung-Ho Liu, Fangchen Li, Hui Goldberg, Ken Robotics Artificial Intelligence We explore how to enhance next-token prediction models to perform in-context imitation learning on a real robot, where the robot executes new tasks by interpreting contextual information provided during the input phase, without updating its underlying policy parameters. We propose In-Context Robot Transformer (ICRT), a causal transformer that performs autoregressive prediction on sensorimotor trajectories without relying on any linguistic data or reward function. This formulation enables flexible and training-free execution of new tasks at test time, achieved by prompting the model with sensorimotor trajectories of the new task composing of image observations, actions and states tuples, collected through human teleoperation. Experiments with a Franka Emika robot demonstrate that the ICRT can adapt to new tasks specified by prompts, even in environment configurations that differ from both the prompt and the training data. In a multitask environment setup, ICRT significantly outperforms current state-of-the-art next-token prediction models in robotics on generalizing to unseen tasks. Code, checkpoints and data are available on https://icrt.dev/ |
| title | In-Context Imitation Learning via Next-Token Prediction |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2408.15980 |