Browse Source

add description for tianshou

master
Icarus 2 months ago
parent
commit
f7217196fa
1 changed files with 6 additions and 6 deletions
  1. +6
    -6
      README.md

+ 6
- 6
README.md View File

@ -17,7 +17,7 @@ cd NeoRL
pip install -e .
```
#### 3. Install tianshou
Please install the newest version of tianshou through GitHub:
We use [tianshou](https://github.com/thu-ml/tianshou), a popular RL framework, to train the behavioral policies. Please install the tianshou through GitHub:
`pip install git+https://github.com/thu-ml/tianshou.git@866e35d`
@ -36,14 +36,14 @@ env = neorl.make("citylearn")
You can use the following environments now:
| Env Name | observation shape | action shape | have done | max timesteps |
| Env Name | observation shape | action shape | have done | max timesteps |
|----------------|-------------------|--------------|-----------|---------------|
| HalfCheetah-v3 |18 |6 |False |1000 |
|HalfCheetah-v3 |18 |6 |False |1000 |
|Hopper-v3 |12 |3 |True |1000 |
|Walker2d-v3 |18 |6 |True |1000 |
|ib |182 |3 |False |1000 |
|finance |181 |30 |False |2516 |
|citylearn |74 |14 |False |1000 |
|ib |182 |3 |False |1000 |
|finance |181 |30 |False |2516 |
|citylearn |74 |14 |False |1000 |
## Usage
### 1.Train policy


Loading…
Cancel
Save