hendoo commited on
Commit
0219bf3
1 Parent(s): 0883271

Upload . with huggingface_hub

Browse files
Files changed (4) hide show
  1. README.md +4 -4
  2. q-learning.pkl +2 -2
  3. replay.mp4 +0 -0
  4. results.json +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  tags:
3
- - Taxi-v3-8x8-no_slippery
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: Taxi-v3-8x8-no_slippery
15
- type: Taxi-v3-8x8-no_slippery
16
  metrics:
17
  - type: mean_reward
18
- value: 0.00 +/- 0.00
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: 7.56 +/- 2.71
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:f60e3dc1235f13ff030cf90febbe8605dbe5ab6d4bad8190d64c6b88289cb093
3
- size 2646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:109aab492b4f3bf27d294899ae6fad148cf14f9cd4fe7aac03cca06c5bf940fa
3
+ size 24570
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "Taxi-v3", "mean_reward": 0.0, "n_eval_episodes": 100, "eval_datetime": "2022-12-16T12:46:13.365524"}
 
1
+ {"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-12-16T12:47:58.968613"}