Iuliu Ranta
commited on
Commit
•
9694a75
1
Parent(s):
edecde0
Upload folder using huggingface_hub
Browse files- README.md +4 -4
- q-learning.pkl +2 -2
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
tags:
|
3 |
-
-
|
4 |
- q-learning
|
5 |
- reinforcement-learning
|
6 |
- custom-implementation
|
@@ -11,11 +11,11 @@ model-index:
|
|
11 |
type: reinforcement-learning
|
12 |
name: reinforcement-learning
|
13 |
dataset:
|
14 |
-
name:
|
15 |
-
type:
|
16 |
metrics:
|
17 |
- type: mean_reward
|
18 |
-
value:
|
19 |
name: mean_reward
|
20 |
verified: false
|
21 |
---
|
|
|
1 |
---
|
2 |
tags:
|
3 |
+
- Taxi-v3
|
4 |
- q-learning
|
5 |
- reinforcement-learning
|
6 |
- custom-implementation
|
|
|
11 |
type: reinforcement-learning
|
12 |
name: reinforcement-learning
|
13 |
dataset:
|
14 |
+
name: Taxi-v3
|
15 |
+
type: Taxi-v3
|
16 |
metrics:
|
17 |
- type: mean_reward
|
18 |
+
value: 7.78 +/- 2.25
|
19 |
name: mean_reward
|
20 |
verified: false
|
21 |
---
|
q-learning.pkl
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 sha256:23f51cd6cbd1911bcc2bf4a14f805af2fd3ed90ef66311d3b25a3072c29fac32
|
3 |
+
size 24368
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"env_id": "
|
|
|
1 |
+
{"env_id": "Taxi-v3", "mean_reward": 7.78, "n_eval_episodes": 100, "eval_datetime": "2023-07-19T08:27:32.300605"}
|