YonV1943 曾伊言
YonV1943 曾伊言
我们想让 `elegantrl_helloworld` 容易安装、运行、阅读。 We want to keep `elegantrl_helloworld` easy to install/ run/ read. - **容易安装**：只需安装 `torch` 和 `gym` - **容易运行**：只有四个核心文件 `agent.py, net.py, run.py, config.py` - **容易阅读**：总代码行数不超过1000行 - **easy to install**:...
Search the funtion `build_env` in ElegantRL. There are: > 21 code results in [AI4Finance-Foundation/ElegantRL](https://github.com/AI4Finance-Foundation/ElegantRL) The `from elegantrl.envs.Gym import build_env` could be changed to `from elegantrl.train.config import build_env` The function `build_env`...
If you have any suggestion about `ElegantRL Helloworld`, you can discuss them here, and **we will keep an eye on this issue**. ElegantRL's code, especially the Helloworld, really needs a...
There are bug in `if_act_target` and `if_cri_target` in `AgentBase.py` `class AgentXXX.__init__()` should set `args.if_cri_target = getattr(self, "if_cri_target", True)` (or False) in default. Takes AgentDQN as an example, the following code...
When creating a neural network, we can specify the network width, but we can't set the number of layers, and I want to add the hyperparameter `num_layer`. To be compatible...
To use `multiprocessing`, the following code should be moved into `if __name__ == '__main__':` https://github.com/AI4Finance-Foundation/ElegantRL/blob/91c1c3d8747d5a3dcf83d4051ba15250b4a750a8/examples/tutorial_BipedalWalker-v3.py#L29-L48 .
After training the agent, many people are not sure how to save and load the policy network after training and see how the agent actually performs in a simulation environment....
Both YAML and JSON are commonly used for storing configuration files, and both have their pros and cons. Advantages of using YAML: - YAML is often considered more readable and...
Update OpenAI gym to gymnasium > In the github of gym, there are: The team that has been maintaining Gym since 2021 has moved all future development to [Gymnasium](https://github.com/Farama-Foundation/Gymnasium), a...
After updating the vectorized env and the corresponding multiprocessing training module, support for the PER algorithm has been affected. Corresponding Pull Request: https://github.com/AI4Finance-Foundation/ElegantRL/pull/269 --- The related issue is as follows,...