Initial commit
Browse files- README.md +1 -1
- a2c-CartPole-v1.zip +2 -2
- a2c-CartPole-v1/data +0 -0
- a2c-CartPole-v1/policy.optimizer.pth +1 -1
- a2c-CartPole-v1/policy.pth +1 -1
- config.json +0 -0
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -10,7 +10,7 @@ model-index:
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
-
value:
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 260.00 +/- 0.00
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
a2c-CartPole-v1.zip
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:e715a1736b9e86d98c255626e33d1d2c2ae67f6ac0056efde7ad05b7f06e30e3
|
3 |
+
size 342202601
|
a2c-CartPole-v1/data
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
a2c-CartPole-v1/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 227166841
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb271ea29db16612f492bcc186d53c5c83e6b69588fbf6b1d3221e88bf12f85a
|
3 |
size 227166841
|
a2c-CartPole-v1/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 113582785
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e8f09092c2dab1d0a8b2a5d2a895e5ef95914c99aa138743452515c200c5932
|
3 |
size 113582785
|
config.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 260.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-07T04:31:33.388894"}
|