Push agent to the Hub
Browse files- README.md +4 -4
- logs/events.out.tfevents.1698070897.527fe3665085.17894.0 +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 |
---
|
@@ -37,14 +37,14 @@ model-index:
|
|
37 |
'wandb_entity': None
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
-
'total_timesteps':
|
41 |
-
'learning_rate':
|
42 |
'num_envs': 8
|
43 |
'num_steps': 128
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.95
|
47 |
-
'gae_lambda': 0.
|
48 |
'num_minibatches': 4
|
49 |
'update_epochs': 5
|
50 |
'norm_adv': True
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: -156.84 +/- 68.01
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
37 |
'wandb_entity': None
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
+
'total_timesteps': 500000
|
41 |
+
'learning_rate': 1e-05
|
42 |
'num_envs': 8
|
43 |
'num_steps': 128
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.95
|
47 |
+
'gae_lambda': 0.95
|
48 |
'num_minibatches': 4
|
49 |
'update_epochs': 5
|
50 |
'norm_adv': True
|
logs/events.out.tfevents.1698070897.527fe3665085.17894.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:418f9deb479f6bf1a986a94372f597605d217016b277c5fbd12aa5c52b071f50
|
3 |
+
size 872088
|
model.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43026
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cb9866b1ef0934d0a4d11aac5359c79822a9e609c18874326fbc774a9fbcc2e
|
3 |
size 43026
|
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": -156.84411362634867, "std_reward": 68.01235352547111, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:26:10.119748"}
|