ThomasSimonini HF staff commited on
Commit
d2ef84e
1 Parent(s): d11320d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -3,6 +3,17 @@ tags:
3
  - deep-reinforcement-learning
4
  - reinforcement-learning
5
  - stable-baselines3
 
 
 
 
 
 
 
 
 
 
 
6
  ---
7
  # PPO Agent playing PongNoFrameskip-v4
8
  This is a trained model of a **PPO agent playing PongNoFrameskip-v4 using the [stable-baselines3 library](https://stable-baselines3.readthedocs.io/en/master/index.html)** (our agent is the 🟢 one).
 
3
  - deep-reinforcement-learning
4
  - reinforcement-learning
5
  - stable-baselines3
6
+ model-index:
7
+ - name: PPO Agent
8
+ results:
9
+ - task:
10
+ type: reinforcement-learning # Required. Example: automatic-speech-recognition
11
+ dataset:
12
+ type: PongNoFrameskip-v4 # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
13
+ name: PongNoFrameskip-v4 # Required. Example: Common Voice zh-CN
14
+ metrics:
15
+ - type: mean_reward # Required. Example: wer
16
+ value: 21 # Required. Example: 20.90
17
  ---
18
  # PPO Agent playing PongNoFrameskip-v4
19
  This is a trained model of a **PPO agent playing PongNoFrameskip-v4 using the [stable-baselines3 library](https://stable-baselines3.readthedocs.io/en/master/index.html)** (our agent is the 🟢 one).