MorvanZhou / Reinforcement-learning-with-tensorflow

Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学
https://mofanpy.com/tutorials/machine-learning/reinforcement-learning/
MIT License
8.84k stars 5k forks source link

Better Exploration with Parameter Noise #35

Closed dynamik1703 closed 6 years ago

dynamik1703 commented 6 years ago

Hey MorvanZhou,

first thanks for your really amazing expert work! Your repo is my favorite GitHub repo to learn about Reinforcement Learning!

Matthias Plappert has presented an impressive alternative to the action noise. It is called Parameter Noise: https://blog.openai.com/better-exploration-with-parameter-noise/ https://github.com/openai/baselines/blob/master/baselines/ddpg/noise.py

Do you think this could be interesting for your repository? To compare and teach it?

Do you think it's easy to embed?

Best, Roman

MorvanZhou commented 6 years ago

Hi I actually did an openai ES method for reinforcement learning, which is a similar method to what you mentioned above. Here is my implementation of that method. https://github.com/MorvanZhou/Evolutionary-Algorithm/blob/master/tutorial-contents/Using%20Neural%20Nets/Evolution%20Strategy%20with%20Neural%20Nets.py

dynamik1703 commented 6 years ago

Evolution strategies are interesting as well for hyperparameter optimization.

Do you have some algorithms for this?