Commit
•
ad6b331
1
Parent(s):
5801b8b
step 8_520_000 . Checkpoint from initial model taken and trained further at a lower learning rate 2nd
Browse files- README.md +1 -1
- ppo-Pixelcopter-PLE-v0.zip +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: Pixelcopter-PLE-v0
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: Pixelcopter-PLE-v0
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 258.10 +/- 236.89
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
ppo-Pixelcopter-PLE-v0.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 147853
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c20f18b593a534772420a2aa30cffa89e5905a3e6ae0444e35ad3b2ffc00710
|
3 |
size 147853
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 258.1, "std_reward": 236.890459917659, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-22T14:31:52.925925"}
|