Assignment 5 has only one task: Atari game playing. Details are shown below.
Assignment 5 is to implement Deep Reinforcement Learning.
TAs will import agent.py and your Github should contain following files:
' ADL2016/hw5/agent.py '
' ADL2016/hw5/best_model.ckpt '
' ADL2016/hw5/report.pdf '
' ADL2016/hw5/download.sh(optional) '
Make sure your code contain those files mentioned above.
TA will evaluate your model by import agent.py and test it with several episode.
Assignment 5 Grading Policy :
- achieving weak baseline gets 4%
- achieving strong baseline get 4% more
Your report 'report.pdf' should follow some rules :
- Answer 3 questions we provided.(see HW slides)
- Up to 2 pages.(include figures)
- Fontsize : 12pt.
- If any wrong format or error occurred, that part will get 0%
- There's "no" need to submit your code to codalab, just upload your files to Github
- For more details, please see homework 5 slides here
General questions; GitHub submission.
General questions; CodaLab submission.