SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling
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.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SPRINT: Efficient Spectral Priors for Humanoid Athletic Sprints
The pursuit of humanoid athletic sprints is hindered by a scarcity of humanoid-viable kinematic reference data and the inability of existing frameworks to maintain stability during sprints. To overcome these limitations,…
Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers
Diffusion Transformers (DiTs) deliver state-of-the-art generative performance but their quadratic training cost with sequence length makes large-scale pretraining prohibitively expensive. Token dropping can reduce traini…
Scalable Sparse Regression for Model Discovery: The Fast Lane to Insight
There exist endless examples of dynamical systems with vast available data and unsatisfying mathematical descriptions. Sparse regression applied to symbolic libraries has quickly emerged as a powerful tool for learning g…
Model DiscoveryregressionScaling Structure Aware Virtual Screening to Billions of Molecules with SPRINT
Virtual screening of small molecules against protein targets can accelerate drug discovery and development by predicting drug-target interactions (DTIs). However, structure-based methods like molecular docking are too sl…
Drug DiscoveryMolecular DockingPolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models
Safety alignment of large language models (LLMs) typically depends on high-quality supervision data, such as safe demonstrations or preference pairs. However, in real-world deployment, emerging safety requirements are of…