LyWangPX / Reinforcement-Learning-2nd-Edition-by-Sutton-Exercise-Solutions

Solutions of Reinforcement Learning, An Introduction
MIT License
2.02k stars 466 forks source link

Add Ex 7.2 #77

Open JChunX opened 3 years ago

JChunX commented 3 years ago

This is my attempt at ex 7.2. For the experiment, I used the Markov reward process found in example 7.1 to compare RMS errors for the original n-step method and the sum of TD errors method.