文件列表:

BrainDQN_NIPS.py (5323, 2017-12-04)
BrainDQN_Nature.py (6883, 2017-12-04)
FlappyBirdDQN.py (1360, 2017-12-04)
assets (0, 2017-12-04)
assets\audio (0, 2017-12-04)
assets\audio\die.ogg (17483, 2017-12-04)
assets\audio\die.wav (194894, 2017-12-04)
assets\audio\hit.ogg (15670, 2017-12-04)
assets\audio\hit.wav (96590, 2017-12-04)
assets\audio\point.ogg (13235, 2017-12-04)
assets\audio\point.wav (177486, 2017-12-04)
assets\audio\swoosh.ogg (13697, 2017-12-04)
assets\audio\swoosh.wav (354638, 2017-12-04)
assets\audio\wing.ogg (7728, 2017-12-04)
assets\audio\wing.wav (29902, 2017-12-04)
assets\sprites (0, 2017-12-04)
assets\sprites\0.png (2879, 2017-12-04)
assets\sprites\1.png (2868, 2017-12-04)
assets\sprites\2.png (2888, 2017-12-04)
assets\sprites\3.png (2877, 2017-12-04)
assets\sprites\4.png (2898, 2017-12-04)
assets\sprites\5.png (2888, 2017-12-04)
assets\sprites\6.png (2885, 2017-12-04)
assets\sprites\7.png (2896, 2017-12-04)
assets\sprites\8.png (2878, 2017-12-04)
assets\sprites\9.png (2892, 2017-12-04)
assets\sprites\background-black.png (4030, 2017-12-04)
assets\sprites\base.png (664, 2017-12-04)
assets\sprites\pipe-green.png (5042, 2017-12-04)
assets\sprites\redbird-downflap.png (2948, 2017-12-04)
assets\sprites\redbird-midflap.png (2949, 2017-12-04)
assets\sprites\redbird-upflap.png (2944, 2017-12-04)
game (0, 2017-12-04)
game\flappy_bird_utils.py (2975, 2017-12-04)
game\wrapped_flappy_bird.py (7866, 2017-12-04)
saved_networks (0, 2017-12-04)
saved_networks\checkpoint (283, 2017-12-04)
saved_networks\network-dqn-50000 (14383675, 2017-12-04)
... ...

## Playing Flappy Bird Using Deep Reinforcement Learning (Based on Deep Q Learning DQN) ## Include NIPS 2013 version and Nature Version DQN I rewrite the code from another repo and make it much simpler and easier to understand Deep Q Network Algorithm from DeepMind The code of DQN is only 160 lines long. To run the code, just type python FlappyBirdDQN.py Since the DQN code is a unique class, you can use it to play other games. ## About the code As a reinforcement learning problem, we knows we need to obtain observations and output actions, and the 'brain' do the processing work. Therefore, you can easily understand the BrainDQN.py code. There are three interfaces: 1. getInitState() for initialization 2. getAction() 3. setPerception(nextObservation,action,reward,terminal) the game interface just need to be able to feed the action to the game and output observation,reward,terminal ## Disclaimer This work is based on the repo: [yenchenlin1994/DeepLearningFlappyBird](https://github.com/yenchenlin1994/DeepLearningFlappyBird.git)

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：