paper-with-me

홈 › Papers

Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration

2024-10-23 · Max Wilcoxson, Qiyang Li, Kevin Frans, Sergey Levine

Unsupervised pretraining has been transformative in many supervised domains. However, applying such ideas to reinforcement learning (RL) presents a unique challenge in that fine-tuning does not involve mimicking task-specific data, but rather exploring and locating the solution through iterative self-improvement. In this work, we study how unlabeled prior trajectory data can be leveraged to learn efficient exploration strategies. While prior data can be used to pretrain a set of low-level skills, or as additional off-policy data for online RL, it has been unclear how to combine these ideas effectively for online exploration. Our method SUPE (Skills from Unlabeled Prior data for Exploration) demonstrates that a careful combination of these ideas compounds their benefits. Our method first extracts low-level skills using a variational autoencoder (VAE), and then pseudo-relabels unlabeled trajectories using an optimistic reward model, transforming prior data into high-level, task-relevant examples. Finally, SUPE uses these transformed examples as additional off-policy data for online RL to learn a high-level policy that composes pretrained low-level skills to explore efficiently. We empirically show that SUPE reliably outperforms prior strategies, successfully solving a suite of long-horizon, sparse-reward tasks. Code: https://github.com/rail-berkeley/supe.

📄 PDF Abstract BibTeX arXiv:2410.18076

Code (1)

rail-berkeley/supe 공식 구현 jax

Tasks

Efficient ExplorationReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Adapting Generalist Robot Policies with Semantic Reinforcement Learning

2026-06-30 · Jagdeep Singh Bhatia, Andrew Wagenmaker, William Chen, Sergey Levine arxiv

Generalist robot policies learn a diverse repertoire of behaviors from large-scale pretraining. In principle, this makes them excellent priors for downstream adaptation via reinforcement learning (RL). In practice, howev…

Reinforcement Learning

Accelerating Reinforcement Learning with Learned Skill Priors

2020-10-22 · Karl Pertsch, Youngwoon Lee, Joseph J. Lim

Intelligent agents rely heavily on prior experience when learning a new task, yet most modern reinforcement learning (RL) approaches learn every task from scratch. One approach for leveraging prior knowledge is to transf…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Integrating Cognitive AI with Generative Models for Enhanced Question Answering in Skill-based Learning

2024-07-28 · Rochan H. Madhusudhana, Rahul K. Dass, Jeanette Luu, Ashok K. Goel

In online learning, the ability to provide quick and accurate feedback to learners is crucial. In skill-based learning, learners need to understand the underlying concepts and mechanisms of a skill to be able to apply it…

Question Answering

Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets

2023-04-18 · Maximilian Du, Suraj Nair, Dorsa Sadigh, Chelsea Finn

Enabling robots to learn novel visuomotor skills in a data-efficient manner remains an unsolved problem with myriad challenges. A popular paradigm for tackling this problem is through leveraging large unlabeled datasets …

Few-Shot Imitation LearningImitation LearningOpen-Ended Question AnsweringRetrieval

DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement

2024-04-03 · CVPR 2024 1 · Hao Wu, Huabin Liu, Yu Qiao, Xiao Sun

We present Dive Into the BoundarieS (DIBS), a novel pretraining framework for dense video captioning (DVC), that elaborates on improving the quality of the generated event captions and their associated pseudo event bound…

Dense Video CaptioningDiversityVideo Captioning