ledmands commited on
Commit
fcbbec7
1 Parent(s): 71d2358

Updated README

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -10,7 +10,7 @@ tags:
10
 
11
  # Agent using DQN to play ALE/Pacman-v5
12
 
13
- ## UPDATE 16 May 2024: Latest DQN model is version 2.6.
14
 
15
  This is an agent that is trained using Stable Baselines3 as part of the capstone project for South Hills School in Spring 2024.
16
  The goal of this project is to gain familiarity with reinforcement learning concepts and tools, and to train an agent to score up into the 400-500 point range in Pacman.
@@ -33,3 +33,6 @@ Currently in major development.
33
  This will plot the evaluation data that was gathered during the training run of the specified agent using MatPlotLib.
34
  Charts can be saved to a directory of the user's choosing.
35
  Currently in major development.
 
 
 
 
10
 
11
  # Agent using DQN to play ALE/Pacman-v5
12
 
13
+ ## UPDATE 16 May 2024: Latest DQN model is version 2.7.
14
 
15
  This is an agent that is trained using Stable Baselines3 as part of the capstone project for South Hills School in Spring 2024.
16
  The goal of this project is to gain familiarity with reinforcement learning concepts and tools, and to train an agent to score up into the 400-500 point range in Pacman.
 
33
  This will plot the evaluation data that was gathered during the training run of the specified agent using MatPlotLib.
34
  Charts can be saved to a directory of the user's choosing.
35
  Currently in major development.
36
+ ### plot_improvement.py
37
+ This plots the score of an agent averaged over all evaluation episodes during a training run. Also plots the
38
+ standard deviation. Removes the lowest and highest episode scores from each evaluation.