Commit
•
481e1b1
1
Parent(s):
c327f1e
Upload . with huggingface_hub
Browse files- README.md +6 -5
- q-learning.pkl +2 -2
- replay.mp4 +2 -2
- results.json +1 -1
README.md
CHANGED
@@ -7,16 +7,17 @@ tags:
|
|
7 |
model-index:
|
8 |
- name: q-Taxi-v3
|
9 |
results:
|
10 |
-
-
|
11 |
-
- type: mean_reward
|
12 |
-
value: 7.56 +/- 2.71
|
13 |
-
name: mean_reward
|
14 |
-
task:
|
15 |
type: reinforcement-learning
|
16 |
name: reinforcement-learning
|
17 |
dataset:
|
18 |
name: Taxi-v3
|
19 |
type: Taxi-v3
|
|
|
|
|
|
|
|
|
|
|
20 |
---
|
21 |
|
22 |
# **Q-Learning** Agent playing **Taxi-v3**
|
|
|
7 |
model-index:
|
8 |
- name: q-Taxi-v3
|
9 |
results:
|
10 |
+
- task:
|
|
|
|
|
|
|
|
|
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: 7.46 +/- 2.79
|
19 |
+
name: mean_reward
|
20 |
+
verified: false
|
21 |
---
|
22 |
|
23 |
# **Q-Learning** Agent playing **Taxi-v3**
|
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:a1d93726092f535e9cdecae94558c04565cb833dd18a078f50c12a33a68a1379
|
3 |
+
size 24570
|
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 sha256:14d66b621bca3d91e72360e8512270819e2a3d9da538083fd310b948319793c7
|
3 |
+
size 120355
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"env_id": "Taxi-v3", "mean_reward": 7.
|
|
|
1 |
+
{"env_id": "Taxi-v3", "mean_reward": 7.46, "n_eval_episodes": 100, "eval_datetime": "2022-12-26T08:53:57.785811"}
|