Push agent to the Hub
Browse files- README.md +8 -8
- logs/events.out.tfevents.1680796520.8d593442c7ec.4040.0 +3 -0
- model.pt +2 -2
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
tags:
|
3 |
-
-
|
4 |
- ppo
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
@@ -13,19 +13,19 @@ model-index:
|
|
13 |
type: reinforcement-learning
|
14 |
name: reinforcement-learning
|
15 |
dataset:
|
16 |
-
name:
|
17 |
-
type:
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
-
value:
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
24 |
|
25 |
-
# PPO Agent Playing
|
26 |
-
|
27 |
-
This is a trained model of a PPO agent playing CartPole-v1.
|
28 |
|
|
|
|
|
29 |
# Hyperparameters
|
30 |
```python
|
31 |
{'exp_name': 'ppo'
|
@@ -36,7 +36,7 @@ model-index:
|
|
36 |
'wandb_project_name': 'cleanRL'
|
37 |
'wandb_entity': None
|
38 |
'capture_video': False
|
39 |
-
'env_id': '
|
40 |
'total_timesteps': 50000
|
41 |
'learning_rate': 0.00025
|
42 |
'num_envs': 4
|
|
|
1 |
---
|
2 |
tags:
|
3 |
+
- LunarLander-v2
|
4 |
- ppo
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
|
|
13 |
type: reinforcement-learning
|
14 |
name: reinforcement-learning
|
15 |
dataset:
|
16 |
+
name: LunarLander-v2
|
17 |
+
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: -177.37 +/- 85.15
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
24 |
|
25 |
+
# PPO Agent Playing LunarLander-v2
|
|
|
|
|
26 |
|
27 |
+
This is a trained model of a PPO agent playing LunarLander-v2.
|
28 |
+
|
29 |
# Hyperparameters
|
30 |
```python
|
31 |
{'exp_name': 'ppo'
|
|
|
36 |
'wandb_project_name': 'cleanRL'
|
37 |
'wandb_entity': None
|
38 |
'capture_video': False
|
39 |
+
'env_id': 'LunarLander-v2'
|
40 |
'total_timesteps': 50000
|
41 |
'learning_rate': 0.00025
|
42 |
'num_envs': 4
|
logs/events.out.tfevents.1680796520.8d593442c7ec.4040.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecccebc69132fada3d0cd071c90dbe9033eb35d852e873c4383257079001070b
|
3 |
+
size 109965
|
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:fb1e581e8ea089e394de546be12d511004e2bf415ffa041b3a747b063f4a10bc
|
3 |
+
size 42597
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"env_id": "
|
|
|
1 |
+
{"env_id": "LunarLander-v2", "mean_reward": -177.37114091008803, "std_reward": 85.14679528417939, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-06T15:56:11.546244"}
|