dodox/fancy_rl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Showcase TRPL in README

Browse Source
This commit is contained in:
Dominik Moritz Roth 2024-05-31 18:25:42 +02:00
parent 1086c9f6fd
commit 5a6069daf4
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -23,11 +23,11 @@ Fancy RL provides two main components:
1. **Ready-to-use Classes for PPO / TRPL**: These classes allow you to quickly get started with reinforcement learning algorithms, enjoying the performance and hackability that comes with using TorchRL.
```python
from fancy_rl import PPO
from fancy_rl import PPO, TRPL
ppo = PPO("CartPole-v1")
model = TRPL("CartPole-v1")
ppo.train()
model.train()
```
For environments, you can pass any [gymnasium](https://gymnasium.farama.org/) or [Fancy Gym](https://alrhub.github.io/fancy_gym/) environment ID as a string, a function returning a gymnasium environment, or an already instantiated gymnasium environment. Future plans include supporting other torchrl environments.