Cheekydave
commited on
Commit
•
24d308b
1
Parent(s):
7420e46
Upload PPO CarRacing-v2 trained agent
Browse files- README.md +1 -1
- config.json +0 -0
- ppo-CarRacing-v2.zip +2 -2
- ppo-CarRacing-v2/data +0 -0
- ppo-CarRacing-v2/policy.optimizer.pth +1 -1
- ppo-CarRacing-v2/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: CarRacing-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: CarRacing-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: -63.73 +/- 2.13
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
ppo-CarRacing-v2.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:f82a7462868fad61fa9ae5d6e722bb8fd3062780f45acfb1fcabbc86d075b1ed
|
3 |
+
size 26327679
|
ppo-CarRacing-v2/data
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
ppo-CarRacing-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17416033
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76c1cee97133d770254234bd2572303c4c1abb9508f2a24fe47ca11792171095
|
3 |
size 17416033
|
ppo-CarRacing-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8710383
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cbbced99c5af6a7bff1363c994562beff57c1fbf0a601893fe31c8f4184c53f
|
3 |
size 8710383
|
replay.mp4
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 sha256:70030481c925292ed26c63c3e4ab6bb0afadeec6ab01791d08148827224b63f3
|
3 |
+
size 227882
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": -63.7287727, "std_reward": 2.1289086971368225, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-23T16:05:33.296900"}
|