snsd0805/TetrisRL
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Implement a reinforcement learning model which can play Tetris
6 Commits 1 Branch 0 Tags 88 KiB
Python 100%
dccbf639e5
Go to file
Ting-Jun Wang dccbf639e5
docs: README
2022-07-02 03:21:00 +08:00
agent.py feat: Policy Gradient, Rewards Delay 2022-07-02 03:13:05 +08:00
enviroment.py feat: Policy Gradient, Rewards Delay 2022-07-02 03:13:05 +08:00
game.py feat: Policy Gradient, Rewards Delay 2022-07-02 03:13:05 +08:00
network.py feat: 新增 RL model & Agent 2022-07-01 03:34:50 +08:00
README.md docs: README 2022-07-02 03:21:00 +08:00
train.py feat: Policy Gradient, Rewards Delay 2022-07-02 03:13:05 +08:00

README.md

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