Update README.md

Author: findmyway

README.md

@@ -89,7 +89,8 @@ If you would like to make some improvements, I'd suggest the following workflow
 | Chapter07 | [fig_7_2](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_7_2.png) | |
 | Chapter08 | [fig_8_2](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_8_2.png), [fig_8_4_example](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_8_4_example.png), [fig_8_4](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_8_4.png) | |
 | | [fig_8_5](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_8_5.png), [fig_8_7](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_8_7.png), [fig_8_8_a](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_8_8_a.png), [fig_8_8_b](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_8_8_b.png) | |
-| Chapter09 | [fig_9_1_a](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_9_1_a.png), [fig_9_1_b](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_9_1_b.png), [fig_9_2_a](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_9_2_a.png), [fig_9_2_b](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_9_2_b.png), [fig_9_5](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_9_5.png), [fig_9_10](https://github.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/blob/master/docs/src/assets/figures/figure_9_10.png)| |
+| Chapter09 | [fig_9_1_a](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_9_1_a.png), [fig_9_1_b](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_9_1_b.png), [fig_9_2_a](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_9_2_a.png), [fig_9_2_b](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_9_2_b.png), [fig_9_5](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_9_5.png)| |
+||[fig_9_10](https://github.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/blob/master/docs/src/assets/figures/figure_9_10.png)|Figure_9_10 is different than the original one on the book. Here I trained another 5000 episodes and found that the RMS with the value function of 50-tilings will decrease in the end.|
 | Chapter10 | [fig_10_1_1](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_10_1_1.png), [fig_10_1_2](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_10_1_2.png), [fig_10_1_3](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_10_1_3.png), [fig_10_1_4](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_10_1_4.png), [fig_10_1_5](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_10_1_5.png) | |
 | | [fig_10_3](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_10_3.png), [fig_10_4](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_10_4.png), [fig_10_5](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_10_5.png)| |
 |Chapter11 | [fig_11_2](https://raw.githubusercontent.com/Ju-jl/ReinforcementLearningAnIntroduction.jl/master/docs/src/assets/figures/figure_11_2.png) | |