Understanding The World Through Action

Abstract

The recent history of machine learning research has taught us that machine learning methods can be most effective when they are provided with very large, high-capacity models, and trained on very large and diverse datasets. This has spurred the community to search for ways to remove any bottlenecks to scale. Often the foremost among such bottlenecks is the need for human effort, including the effort of curating and labeling datasets. As a result, considerable attention in recent years has been devoted to utilizing unlabeled data, which can be collected in vast quantities. However, some of the most widely used methods for training on such unlabeled data themselves require human-designed objective functions that must correlate in some meaningful way to downstream tasks. I will argue that a general, principled, and powerful framework for utilizing unlabeled data can be derived from reinforcement learning, using general purpose unsupervised or self-supervised reinforcement learning objecti

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylevine2021understanding

Related papers

• On The Importance Of Data Collection For Training General Goal-reaching Policies (2022)0.00
• Generalizing Skills With Semi-supervised Reinforcement Learning (2016)0.00
• Learning To Act Without Actions (2023)0.00
• Unsupervisedly Learned Representations: Should The Quest Be Over? (2020)0.00
• Generalization Through The Lens Of Learning Dynamics (2022)0.00
• Interpretable Learning Dynamics In Unsupervised Reinforcement Learning (2025)0.00
• Unsupervised Meta-learning For Reinforcement Learning (2018)0.00
• Mapping Out The Space Of Human Feedback For Reinforcement Learning: A Conceptual Framework (2024)0.00