Upload folder using huggingface_hub
Browse files- README.md +37 -1
- hyperparameters.json +1 -1
- model.pt +2 -2
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
|
@@ -16,11 +16,47 @@ model-index:
|
|
| 16 |
type: CartPole-v1
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
-
value:
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
# **Reinforce** Agent playing **CartPole-v1**
|
| 25 |
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
|
| 26 |
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
|
|
|
| 16 |
type: CartPole-v1
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
+
value: 491.56 +/- 59.08
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
| 23 |
|
| 24 |
+
---
|
| 25 |
+
{
|
| 26 |
+
"tags": [
|
| 27 |
+
"CartPole-v1",
|
| 28 |
+
"reinforce",
|
| 29 |
+
"reinforcement-learning",
|
| 30 |
+
"custom-implementation",
|
| 31 |
+
"deep-rl-class"
|
| 32 |
+
],
|
| 33 |
+
"model-index": [
|
| 34 |
+
{
|
| 35 |
+
"name": "Reinforce-CartPole-v1",
|
| 36 |
+
"results": [
|
| 37 |
+
{
|
| 38 |
+
"task": {
|
| 39 |
+
"type": "reinforcement-learning",
|
| 40 |
+
"name": "reinforcement-learning"
|
| 41 |
+
},
|
| 42 |
+
"dataset": {
|
| 43 |
+
"name": "CartPole-v1",
|
| 44 |
+
"type": "CartPole-v1"
|
| 45 |
+
},
|
| 46 |
+
"metrics": [
|
| 47 |
+
{
|
| 48 |
+
"type": "mean_reward",
|
| 49 |
+
"value": "491.56 +/- 59.08",
|
| 50 |
+
"name": "mean_reward",
|
| 51 |
+
"verified": false
|
| 52 |
+
}
|
| 53 |
+
]
|
| 54 |
+
}
|
| 55 |
+
]
|
| 56 |
+
}
|
| 57 |
+
]
|
| 58 |
+
}
|
| 59 |
+
---
|
| 60 |
# **Reinforce** Agent playing **CartPole-v1**
|
| 61 |
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
|
| 62 |
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
hyperparameters.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes":
|
|
|
|
| 1 |
+
{"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 50, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f60e21341904aa1b5f0e8af7b6655fbf8b4ee34ed539247e9e1eb7149669fcc5
|
| 3 |
+
size 3200
|
replay.mp4
CHANGED
|
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"env_id": "CartPole-v1", "mean_reward":
|
|
|
|
| 1 |
+
{"env_id": "CartPole-v1", "mean_reward": 491.56, "n_evaluation_episodes": 50, "eval_datetime": "2025-02-22T22:23:34.405215"}
|