SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917577290153984 |
|---|---|
| author | Zhang, Jesse Pertsch, Karl Zhang, Jiahui Lim, Joseph J. |
| author_facet | Zhang, Jesse Pertsch, Karl Zhang, Jiahui Lim, Joseph J. |
| contents | Pre-training robot policies with a rich set of skills can substantially accelerate the learning of downstream tasks. Prior works have defined pre-training tasks via natural language instructions, but doing so requires tedious human annotation of hundreds of thousands of instructions. Thus, we propose SPRINT, a scalable offline policy pre-training approach which substantially reduces the human effort needed for pre-training a diverse set of skills. Our method uses two core ideas to automatically expand a base set of pre-training tasks: instruction relabeling via large language models and cross-trajectory skill chaining through offline reinforcement learning. As a result, SPRINT pre-training equips robots with a much richer repertoire of skills. Experimental results in a household simulator and on a real robot kitchen manipulation task show that SPRINT leads to substantially faster learning of new long-horizon tasks than previous pre-training approaches. Website at https://clvrai.com/sprint. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_11886 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling Zhang, Jesse Pertsch, Karl Zhang, Jiahui Lim, Joseph J. Robotics Artificial Intelligence Machine Learning Pre-training robot policies with a rich set of skills can substantially accelerate the learning of downstream tasks. Prior works have defined pre-training tasks via natural language instructions, but doing so requires tedious human annotation of hundreds of thousands of instructions. Thus, we propose SPRINT, a scalable offline policy pre-training approach which substantially reduces the human effort needed for pre-training a diverse set of skills. Our method uses two core ideas to automatically expand a base set of pre-training tasks: instruction relabeling via large language models and cross-trajectory skill chaining through offline reinforcement learning. As a result, SPRINT pre-training equips robots with a much richer repertoire of skills. Experimental results in a household simulator and on a real robot kitchen manipulation task show that SPRINT leads to substantially faster learning of new long-horizon tasks than previous pre-training approaches. Website at https://clvrai.com/sprint. |
| title | SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2306.11886 |