Merge pull request #221 from huangshiyu13/main

update

Author: huangshiyu13

README.md

@@ -59,7 +59,7 @@ Currently, the features supported by OpenRL include:
 - Reinforcement learning training support for natural language tasks (such as dialogue)
 
 - Support [Arena](https://openrl-docs.readthedocs.io/en/latest/arena/index.html) , which allows convenient evaluation of
-  various agents in a competitive environment.
+  various agents (even submissions for [JiDi](https://openrl-docs.readthedocs.io/en/latest/arena/index.html#performing-local-evaluation-of-agents-submitted-to-the-jidi-platform-using-openrl)) in a competitive environment.
 
 - Importing models and datasets from [Hugging Face](https://huggingface.co/)
 

README_zh.md

@@ -51,7 +51,7 @@ OpenRL基于PyTorch进行开发，目标是为强化学习研究社区提供一
 - 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[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（甚至是[及第平台](https://openrl-docs.readthedocs.io/zh/latest/arena/index.html#openrl)上提交的智能体）进行评测。
 - 支持从[Hugging Face](https://huggingface.co/)上导入模型和数据
 - 提供用户自有环境接入OpenRL的[详细教程](https://openrl-docs.readthedocs.io/zh/latest/custom_env/index.html).
 - 支持LSTM，GRU，Transformer等模型

examples/arena/README.md

@@ -1,6 +1,17 @@
 
-## Usage
+### Installation
+
+```bash
+pip install "openrl[selfplay]"
+```
+
+### Usage
 
 ```shell
 python run_arena.py
-```
+```
+
+
+### Evaluate Google Research Football submissions for JiDi locally
+
+If you want to evaluate your Google Research Football submissions for JiDi locally, please try to use tizero as illustrated [here](foothttps://github.com/OpenRL-Lab/TiZero#evaluate-jidi-submissions-locally).

examples/gfootball/README.md

@@ -8,7 +8,7 @@ This is the guidance for [Google Research Football](https://github.com/google-re
 
 ### Evaluate JiDi submissions locally
 
-If you want to evaluate your JiDi submissions locally, please try to use tizero as illustrated [here](https://github.com/OpenRL-Lab/TiZero#evaluate-jidi-submissions-locally).
+If you want to evaluate your JiDi submissions locally, please try to use tizero as illustrated [here](foothttps://github.com/OpenRL-Lab/TiZero#evaluate-jidi-submissions-locally).
 
 
 ### Convert dump file to video

examples/selfplay/README.md

@@ -13,10 +13,15 @@ python train_selfplay.py
 ```
 
 
-## Play with a trained agent
+## Play with a Trained Agent
 
 Users can play with a trained agent via:
 
 ```shell
 python human_vs_agent.py
-```
+```
+
+
+## Evaluate Trained Agents
+
+If you want to evaluate your trained agents, please try to use OpenRL Arena as illustrated [here](https://openrl-docs.readthedocs.io/en/latest/arena/index.html)

examples/snake/README.md

@@ -1,19 +1,19 @@
 
 This is the example for the snake game.
 
-## Installation
+### Installation
 
 ```bash
 pip install "openrl[selfplay]"
 ```
 
-## Usage
+### Usage
 
 ```bash
 python train_selfplay.py
 ```
 
-## Evaluate JiDi submissions locally
+### Evaluate JiDi submissions locally
 
 ```bash
 python jidi_eval.py
@@ -26,3 +26,9 @@ Submition site: http://www.jidiai.cn/env_detail?envid=1.
 Snake senarios: [here](https://github.com/jidiai/ai_lib/blob/7a6986f0cb543994277103dbf605e9575d59edd6/env/config.json#L94)
 Original Snake environment: [here](https://github.com/jidiai/ai_lib/blob/master/env/snakes.py)
 
+
+
+
+### Evaluate Google Research Football submissions for JiDi locally
+
+If you want to evaluate your Google Research Football submissions for JiDi locally, please try to use tizero as illustrated [here](foothttps://github.com/OpenRL-Lab/TiZero#evaluate-jidi-submissions-locally).