文件名称:DQN-PyTorch:深度Q网络的PyTorch实现
文件大小:87KB
文件格式:ZIP
更新时间:2024-05-18 06:49:15
deep-learning pytorch reinforcement-learning-algorithms Python
DQN-PyTorch 实现PyTorch 目录: 项目结构: ├── agents | └── dqn.py # the main training agent for the dqn ├── graphs | └── models | | └── dqn.py | └── losses | | └── huber_loss.py # contains huber loss definition ├── datasets # contains all dataloaders for the project ├── utils # utilities folder containing input extraction, replay memory, config parsing, etc | └── assets | └── replay_memory.py |
【文件预览】:
DQN-PyTorch-master
----graphs()
--------models()
--------losses()
--------__init__.py(393B)
--------weights_initializer.py(1KB)
----utils()
--------misc.py(1KB)
--------config.py(2KB)
--------__init__.py(393B)
--------assets()
--------metrics.py(2KB)
--------env_utils.py(2KB)
--------replay_memory.py(896B)
--------dirs.py(422B)
----agents()
--------__init__.py(393B)
--------dqn.py(10KB)
----configs()
--------dqn_exp_0.json(722B)
----main.py(851B)
----run.sh(107B)
----requirements.txt(221B)
----.idea()
--------misc.xml(191B)
--------workspace.xml(32KB)
--------DQN-Pytorch.iml(437B)
--------modules.xml(274B)
--------vcs.xml(180B)
----datasets()
--------__init__.py(394B)
----LICENSE(1KB)
----README.md(2KB)
----.gitignore(1KB)