Quantifying Generalization in Reinforcement Learning
arxiv.org · 5,737 words · saved by 1 readers
N/A
Quantifying Generalization in Reinforcement Learning Karl Cobbe 1 Oleg Klimov 1 Chris Hesse 1 Taehoon Kim 1 John Schulman 1 Abstract (Nichol et al., 2018), we seek to better quantify an agent’s In this paper, we investigate the problem of over- ability to generalize. fitting in deep reinforcement learning. Among To begin,…
saved by
related reading
- Just Ask for Generalization | Eric Jangevjang.com
- Debugging Reinforcement Learning Systemsandyljones.com
- Understanding deep learning requires rethinking generalizationarxiv.org
- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasetsmathai-iclr.github.io
- The upcoming GPT-3 moment for RL | Mechanize, Inc.mechanize.work
- [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
- Composer2.pdfcursor.com
- Verifying your browser | OpenReviewopenreview.net
- How DeepMind's Generally Capable Agents Were Trained — LessWronglesswrong.com
- [1912.02178] Fantastic Generalization Measures and Where to Find Themarxiv.org
- A Taxonomy of RL Environments for LLM Agentsleehanchung.github.io
- To Understand Language is to Understand Generalization | Eric Jangevjang.com