2103.04551
arxiv.org · 7,264 words · saved by 1 readers
N/A
Behavior From the Void: Unsupervised Active Pre-Training Hao Liu Pieter Abbeel UC Berkeley UC Berkeley hao.liu@cs.berkeley.edu pabbeel@cs.berkeley.edu arXiv:2103.04551v4 [cs.LG] 28 Oct 2021…
saved by
related reading
- [2103.04551] Behavior From the Void: Unsupervised Active Pre-Trainingar5iv.labs.arxiv.org
- The upcoming GPT-3 moment for RL | Mechanize, Inc.mechanize.work
- [2602.11399] Can We Really Learn One Representation to Optimize All Rewards?arxiv.org
- Just Ask for Generalization | Eric Jangevjang.com
- Decoupling Representation Learning from Reinforcement Learningarxiv.org
- [2206.11795] Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videosarxiv.org
- RL is even more information inefficient than you thoughtdwarkesh.com
- State of RL for reasoning LLMs | A. Weersaweers.de
- 2312.10812arxiv.org
- Key Papers in Deep RL - Spinning Up documentationspinningup.openai.com
- pistar06.pdfpi.website
- Learning to Act without Actionsarxiv.org