What is wrong with reinforcement learning? (Ep. 82)
Audio is streamed directly from the publisher (mcdn.podbean.com) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
Join the discussion on our Discord server
After reinforcement learning agents doing great at playing Atari video games, Alpha Go, doing financial trading, dealing with language modeling, let me tell you the real story here.
In this episode I want to shine some light on reinforcement learning (RL) and the limitations that every practitioner should consider before taking certain directions. RL seems to work so well! What is wrong with it?
Are you a listener of Data Science at Home podcast?
A reader of the Amethix Blog?
Or did you subscribe to the Artificial Intelligence at your fingertips newsletter?
In any case let’s stay in touch!
https://amethix.com/survey/
References
- Emergence of Locomotion Behaviours in Rich Environments
https://arxiv.org/abs/1707.02286 - Rainbow: Combining Improvements in Deep Reinforcement Learning
https://arxiv.org/abs/1710.02298 - AlphaGo Zero: Starting from scratch
https://deepmind.com/blog/article/alphago-zero-starting-scratch