✳flâneur — a map of the web's best reading
Reinforcement learning is supervised learning on optimized data – The Berkeley Artificial Intelligence Research Blog
bair.berkeley.edu · 2,570 words · saved by 1 readers
The BAIR Blog
The two most common perspectives on Reinforcement learning (RL) are optimization and dynamic programming . Methods that compute the gradients of the non-differentiable expected reward objective, such as the REINFORCE trick are commonly grouped into the optimization perspective, whereas methods that employ TD-learning or Q-learning are dynamic programming methods. While these methods have shown considerable success in recent years, these methods are still quite challenging to apply to new problems. In contrast deep supervised learning has been extremely successful and we may hence ask: Can we u
Explore this link on the map →related reading
- A (Long) Peek into Reinforcement Learning | Lil'Loglilianweng.github.io
- Part 1: Key Concepts in RL - Spinning Up documentationspinningup.openai.com
- Reward is not the optimization target — LessWronglesswrong.com
- Just Ask for Generalization | Eric Jangevjang.com
- Reinforcement learning - Wikipediaen.wikipedia.org
- Reinforcement Learning via Implicit Imitation Guidancearxiv.org
- State of RL for reasoning LLMs | A. Weersaweers.de
- [1707.06347] Proximal Policy Optimization Algorithmsarxiv.org
- An Updated Introduction to Reinforcement Learning | Sri's Blogsrianumakonda.com
- pistar06.pdfpi.website
- Should I Use Offline RL or Imitation Learning? – The Berkeley Artificial Intelligence Research Blogbair.berkeley.edu
- SFT, RL, and On-Policy Distillation Through a Distributional Lens | whnrehiew.github.io