12 lines
206 B
Markdown
12 lines
206 B
Markdown
# TetrisRL
|
|
- Implement a reinforcement learning model which can play Tetris
|
|
|
|
# Version 0
|
|
- Policy Gradient Algorithm
|
|
- Reward Delay
|
|
- Bad Performance
|
|
|
|
# TODO
|
|
- change reward function
|
|
- reward baseline
|
|
- DQN |