Deep Reinforcement Learning Doesn't Work Yet

June 24, 2018 note: If you want to cite an example from the post, please cite the paper which that example came from. If you want to cite the post as a whole, you can use the following BibTeX:

June 24, 2018 note: If you want to cite an example from the post, please cite the paper which that example came from. If you want to cite the post as a whole, you can use the following BibTeX: @misc{rlblogpost, title={Deep Reinforcement Learning Doesn't Work Yet}, author={Irpan, Alex}, howpublished={\url{https://www.alexirpan.com/2018/02/14/rl-hard.html}}, year={2018} } This mostly cites papers from Berkeley, Google Brain, DeepMind, and OpenAI from the past few years, because that work is most visible to me. I’m almost certainly missing stuff from older literature and other institutions, and f

related reading

• Debugging Reinforcement Learning Systemsandyljones.com
• [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
• Reward Hacking in Reinforcement Learning | Lil'Loglilianweng.github.io
• Key Papers in Deep RL - Spinning Up documentationspinningup.openai.com
• A (Long) Peek into Reinforcement Learning | Lil'Loglilianweng.github.io
• Part 1: Key Concepts in RL - Spinning Up documentationspinningup.openai.com
• Just Ask for Generalization | Eric Jangevjang.com
• Deep Reinforcement Learning from Human Preferencesproceedings.neurips.cc
• State of RL for reasoning LLMs | A. Weersaweers.de
• If it makes you feel any better, I've been doing this for a while and it took me... | Hacker Newsnews.ycombinator.com
• Q-learning is not yet scalableseohong.me
• Reward is not the optimization target — LessWronglesswrong.com