Merge pull request #195 from huangshiyu13/main

update readme

Author: huangshiyu13

README.md

@@ -55,7 +55,9 @@ Currently, the features supported by OpenRL include:
 
 - Reinforcement learning training support for natural language tasks (such as dialogue)
 
-- Importing models and datasets from [Hugging Face](https://huggingface.co/)
+- Support [Arena](https://openrl-docs.readthedocs.io/en/latest/arena/index.html) , which allows convenient evaluation of various agents in a competitive environment.
+
+- Importing models and datasets from [Hugging F[README_zh.md](README_zh.md)ace](https://huggingface.co/)
 
 - Support for models such as LSTM, GRU, Transformer etc.
 

README_zh.md

@@ -49,6 +49,7 @@ OpenRL是一个开源的通用强化学习研究框架，支持单智能体、
 - 支持通过专家数据进行离线强化学习训练
 - 支持自博弈训练
 - 支持自然语言任务（如对话任务）的强化学习训练
+- 支持[竞技场](https://openrl-docs.readthedocs.io/zh/latest/arena/index.html))功能，可以在多智能体对抗性环境中方便地对各种智能体进行评测。
 - 支持从[Hugging Face](https://huggingface.co/)上导入模型和数据
 - 支持LSTM，GRU，Transformer等模型
 - 支持多种训练加速，例如：自动混合精度训练，半精度策略网络收集数据等