itsdhanoob
commited on
Commit
•
2ad43c6
1
Parent(s):
b29501f
Push agent to the Hub
Browse files- README.md +8 -8
- logs/events.out.tfevents.1707918178.0b5757c85070.10124.0 +3 -0
- model.pt +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -17,7 +17,7 @@ model-index:
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
-
value:
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
@@ -38,13 +38,13 @@ model-index:
|
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
'total_timesteps': 500000
|
41 |
-
'learning_rate': 0.
|
42 |
-
'num_envs':
|
43 |
-
'num_steps':
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
-
'gamma': 0.
|
47 |
-
'gae_lambda': 0.
|
48 |
'num_minibatches': 4
|
49 |
'update_epochs': 4
|
50 |
'norm_adv': True
|
@@ -55,7 +55,7 @@ model-index:
|
|
55 |
'max_grad_norm': 0.5
|
56 |
'target_kl': None
|
57 |
'repo_id': 'itsdhanoob/cleanRlPPO-lunar_lander'
|
58 |
-
'batch_size':
|
59 |
-
'minibatch_size':
|
60 |
```
|
61 |
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: -164.42 +/- 70.38
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
'total_timesteps': 500000
|
41 |
+
'learning_rate': 0.0003
|
42 |
+
'num_envs': 16
|
43 |
+
'num_steps': 1024
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
+
'gamma': 0.999
|
47 |
+
'gae_lambda': 0.98
|
48 |
'num_minibatches': 4
|
49 |
'update_epochs': 4
|
50 |
'norm_adv': True
|
|
|
55 |
'max_grad_norm': 0.5
|
56 |
'target_kl': None
|
57 |
'repo_id': 'itsdhanoob/cleanRlPPO-lunar_lander'
|
58 |
+
'batch_size': 16384
|
59 |
+
'minibatch_size': 4096}
|
60 |
```
|
61 |
|
logs/events.out.tfevents.1707918178.0b5757c85070.10124.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f317c2e428cae882d1f9087bec8a3755edc251421b4d65c51d74f884252085ff
|
3 |
+
size 601284
|
model.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 42898
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8374edaaf6963c589e942b7f6e6734de8152e1075152bf569a4022089adbd40
|
3 |
size 42898
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"env_id": "LunarLander-v2", "mean_reward":
|
|
|
1 |
+
{"env_id": "LunarLander-v2", "mean_reward": -164.41853578840528, "std_reward": 70.38290400359136, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-14T13:46:03.124109"}
|