TF2RL是一个深度强化学习库，你可以使用TensorFlow 2.0实现各种深度强化学习算法。

Github项目地址：https://github.com/keiohta/tf2rl

算法

项目支持以下算法：

以下论文已在tf2rl中实现：

Model-free On-policy RL 无模型策略强化学习

• Policy Gradient Methods for Reinforcement Learning with Function Approximation, code

• High-Dimensional Continuous Control Using Generalized Advantage Estimation, code

Model-free Off-policy RL 无模型离策略强化学习

• Playing Atari with Deep Reinforcement Learning, code

• Human-level control through Deep Reinforcement Learning, code

• Deep Reinforcement Learning with Double Q-learning, code

• Prioritized Experience Replay, code

• Dueling Network Architectures for Deep Reinforcement Learning, code

• A Distributional Perspective on Reinforcement Learning, code

• Noisy Networks for Exploration, code

• Distributed Prioritized Experience Replay, code

• Continuous control with deep reinforcement learning, code

• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor, code

• Addressing Function Approximation Error in Actor-Critic Methods, code

• Deep Residual Reinforcement Learning, code

Imitation Learning 模仿学习

• Generative Adversarial Imitation Learning, code

• Spectral Normalization for Generative Adversarial Networks, code

安装

你可以从PyPI中安装tf2rl：

$ pip install tf2rl

或者，你也可以从源代码安装：

$ git clone https://github.com/keiohta/tf2rl.git tf2rl$ cd tf2rl$ pip install .

入门

以下是如何在Pendulum环境中训练DDPG代理的快速示例：

import gymfrom tf2rl.algos.ddpg import DDPGfrom tf2rl.experiments.trainer import Trainer parser = Trainer.get_argument() parser = DDPG.get_argument(parser) args = parser.parse_args() env = gym.make("Pendulum-v0") test_env = gym.make("Pendulum-v0") policy = DDPG( state_shape=env.observation_space.shape, action_dim=env.action_space.high.size, gpu=-1, # Run on CPU. If you want to run on GPU, specify GPU number memory_capacity=10000, max_action=env.action_space.high[0], batch_size=32, n_warmup=500) trainer = Trainer(policy, env, args, test_env=test_env) trainer()

你可以在示例中检查已实现的算法。 例如，如果你想训练DDPG代理：

# You must change directory to avoid importing local files.$ cd examples$ python run_ddpg.py