mwc/lab_reinforcement_learning
Template
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update questions

Browse Source
This commit is contained in:
Chris Proctor
2026-06-26 21:30:22 -04:00
parent 482f4f6cfa
commit d83a3b7e4b
1 changed files with 3 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
questions.md
View File

@@ -53,17 +53,7 @@
## Checkpoint 5
Answer these questions after completing both training experiments in "Training Frogger."
14. Describe the strategies you tried across your three training attempts. What was your motivation
for each change? How well did each work? Use evidence from the training log or plot in your answer.
14. **Hypothesis (Attempt 1):** Before training, predict what will happen. Will the agent learn to
reach the top of the board? What challenge do you think it will face?
15. **Evidence (Attempt 1):** Copy the first three and last three lines of `runs/frogger/training.log`.
Did training go as expected?
16. **Analysis (Attempt 1):** What did the agent learn to do? Where did it struggle?
17. **Experiment (Attempt 2):** What one thing did you change? Write your prediction, show the
evidence (first and last few log lines), and describe what happened.
18. Which attempt produced the best agent? What would you try next if you had more time?
15. Watch your most successful agent play Frogger a few times. What are its strengths and weaknesses?