文件列表:

A2C (0, 2019-06-24)
A2C\agent.py (2872, 2019-06-24)
A2C\model.py (905, 2019-06-24)
A2C\test.py (124, 2019-06-24)
DDPG (0, 2019-06-24)
DDPG\agent.py (4417, 2019-06-24)
DDPG\model.py (1262, 2019-06-24)
DDPG\test.py (1284, 2019-06-24)
DDPG\utils.py (2811, 2019-06-24)
DQN (0, 2019-06-24)
DQN\agent.py (3439, 2019-06-24)
DQN\model.py (1587, 2019-06-24)
DQN\test.py (160, 2019-06-24)
DQN\utils.py (9699, 2019-06-24)
DRQN (0, 2019-06-24)
DRQN\model.py (1, 2019-06-24)
Double_DQN (0, 2019-06-24)
Double_DQN\__pycache__ (0, 2019-06-24)
Double_DQN\__pycache__\agent.cpython-36.pyc (3408, 2019-06-24)
Double_DQN\__pycache__\model.cpython-36.pyc (1962, 2019-06-24)
Double_DQN\__pycache__\utils.cpython-36.pyc (11276, 2019-06-24)
Double_DQN\agent.py (6020, 2019-06-24)
Double_DQN\model.py (1587, 2019-06-24)
Double_DQN\test.py (160, 2019-06-24)
Double_DQN\utils.py (9699, 2019-06-24)
Dueling_DQN (0, 2019-06-24)
Dueling_DQN\__pycache__ (0, 2019-06-24)
Dueling_DQN\__pycache__\agent.cpython-36.pyc (2906, 2019-06-24)
Dueling_DQN\__pycache__\model.cpython-36.pyc (2201, 2019-06-24)
Dueling_DQN\__pycache__\utils.cpython-36.pyc (11270, 2019-06-24)
Dueling_DQN\agent.py (3337, 2019-06-24)
Dueling_DQN\model.py (2232, 2019-06-24)
Dueling_DQN\test.py (160, 2019-06-24)
Dueling_DQN\utils.py (9701, 2019-06-24)
LICENSE (1067, 2019-06-24)
REINFORCE (0, 2019-06-24)
REINFORCE\reinforce.py (4529, 2019-06-24)
... ...

# Reinforcement-Learning Modular implementations of reinforcement learning algorithms ## I will be gradually refactoring and moving the implementation to different repositories!! - **Algorithms from the Q learning family will be moved to https://github.com/cyoon1729/deep-Q-networks.** - **Algorithms from the PG family will be moved to another repository as well, which has not been created yet.** # Is done: - REINFORCE - DQN - Double DQN - Dueling DQN - A2C - DDPG # Requirements: - Python 3 - PyTorch 0.4.1 - OpenAI Gym

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：