pushing model

README.md

@@ -15,7 +15,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 70.00 +/- 19.16
+      value: 65.80 +/- 13.11
       name: mean_reward
       verified: false
 ---
@@ -26,6 +26,11 @@ This is a trained model of a DQN agent playing CartPole-v1.
 The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the training code can be
 found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/dqn.py).
 
+## Command to reproduce the training
+
+```bash
+dqn.py --cuda False --save-model --upload-model --total-timesteps 500
+
 
 # Hyperparameters
 ```python
@@ -46,7 +51,7 @@ found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/dqn.py).
  'start_e': 1,
  'target_network_frequency': 500,
  'torch_deterministic': True,
- 'total_timesteps': 10000,
+ 'total_timesteps': 500,
  'track': False,
  'train_frequency': 10,
  'upload_model': True,

events.out.tfevents.1668612313.pop-os.1028360.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e3b97f1606139c2589cd8db6c6a49be58d467d90cd8a2f6d4bce7795290fde
+size 1805

events.out.tfevents.1668612314.pop-os.1028360.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a81d131d629717b87468b6c4231deffe55099b4f6b20aa9e7766c73eda75e4cb
+size 618

q_network.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37569e0ac54f61ecf5dde3387ec06184d48efe905501c80dd239668e91bf5884
-size 45783
+oid sha256:574158aedd6795b4ae67e7e916a05b146481d57fbb5e8a78fad770e289fb43fa
+size 45927