search

MJeremy2017 / reinforcement-learning-implementation

Reinforcement Learning examples implementation and explanation
MIT License
318 stars 242 forks source link

TD Lambda - Reset z #4

Open thiagolcks opened 4 years ago

thiagolcks commented 4 years ago

Shouldn't you reset z at the beginning of each episode? Otherwise, after the first steps it will also update the weights of the latest steps of the previous episode.

From your post: https://miro.medium.com/max/1400/1*G3bXDd1QeeUphO0RyQOgVA.png

Thanks for this amazing repository! :)

MJeremy2017 commented 4 years ago

sorry, may I know which file you are pointing to?