Stefano Ermon, Jiaming Song, Divyansh Garg, Kuno Kim, Skanda Vaidyanath
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Learning policies that effectively utilize language instructions in complex, multitask environments is an important problem in sequential decision-making. While it is possible to condition on the entire language instruction directly, such an approach could suffer from generalization issues. In our work, we propose Learning Interpretable Skill Abstractions (LISA), a hierarchical imitation learning framework that can learn diverse, interpretable primitive behaviors or skills from languageconditioned demonstrations to better generalize to unseen instructions. LISA uses vector quantization to learn discrete skill codes that are highly correlated with language instructions and the behavior of the learned policy. In navigation and robotic manipulation tasks, LISA outperforms a strong non-hierarchical Decision Transformer baseline in the low data regime and is able to compose learned skills to solve tasks containing unseen long-range instructions. Our method demonstrates a more natural way to condition on language in sequential decision-making problems and achieve interpretable and controllable behavior with the learned skills.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.00054")
get_code_for_paper("2203.00054")
have("2203.00054")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.00054.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.00054)
Connect an agent — have() is free.