Commit
•
aa9742a
1
Parent(s):
9066b3f
Push agent to the Hub
Browse files- README.md +40 -16
- logs/events.out.tfevents.1679550943.598eee5fcdd7.3644.0 +3 -0
- model.pt +3 -0
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -1,10 +1,11 @@
|
|
1 |
---
|
2 |
-
library_name: stable-baselines3
|
3 |
tags:
|
4 |
- LunarLander-v2
|
|
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
7 |
-
-
|
|
|
8 |
model-index:
|
9 |
- name: PPO
|
10 |
results:
|
@@ -16,22 +17,45 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
23 |
|
24 |
-
#
|
25 |
-
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
26 |
-
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- LunarLander-v2
|
4 |
+
- ppo
|
5 |
- deep-reinforcement-learning
|
6 |
- reinforcement-learning
|
7 |
+
- custom-implementation
|
8 |
+
- deep-rl-course
|
9 |
model-index:
|
10 |
- name: PPO
|
11 |
results:
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: -162.34 +/- 97.71
|
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 |
+
{'repo_id': 'ThePianist/ppo-LunarLander-v2'
|
32 |
+
'exp_name': 'ppo'
|
33 |
+
'seed': 1
|
34 |
+
'torch_deterministic': True
|
35 |
+
'cuda': True
|
36 |
+
'track': False
|
37 |
+
'wandb_project_name': 'cleanRL'
|
38 |
+
'wandb_entity': None
|
39 |
+
'capture_video': False
|
40 |
+
'env_id': 'LunarLander-v2'
|
41 |
+
'total_timesteps': 50000
|
42 |
+
'learning_rate': 0.00025
|
43 |
+
'num_envs': 4
|
44 |
+
'num_steps': 128
|
45 |
+
'anneal_lr': True
|
46 |
+
'gae': True
|
47 |
+
'gamma': 0.99
|
48 |
+
'gae_lambda': 0.95
|
49 |
+
'num_minibatches': 4
|
50 |
+
'update_epochs': 4
|
51 |
+
'norm_adv': True
|
52 |
+
'clip_coef': 0.2
|
53 |
+
'clip_vloss': True
|
54 |
+
'ent_coef': 0.01
|
55 |
+
'vf_coef': 0.5
|
56 |
+
'max_grad_norm': 0.5
|
57 |
+
'target_kl': None
|
58 |
+
'batch_size': 512
|
59 |
+
'minibatch_size': 128}
|
60 |
+
```
|
61 |
+
|
logs/events.out.tfevents.1679550943.598eee5fcdd7.3644.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f960d9778e87313a0bc587b712fe35e5c5c2b92ae5a51bc6f15fc7263212ceeb
|
3 |
+
size 111163
|
model.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
|
3 |
+
size 42597
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"env_id": "LunarLander-v2", "mean_reward": -162.3442758493183, "std_reward": 97.70804096837816, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-23T05:56:30.792936"}
|