bothrajat commited on
Commit
74448fa
1 Parent(s): 9014a60

Push Q-Learning agent to Hub

Browse files
Files changed (3) hide show
  1. README.md +4 -4
  2. replay.mp4 +2 -2
  3. results.json +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  tags:
3
- - Taxi-v3-4x4-no_slippery
4
  - q-learning
5
  - reinforcement-learning
6
  - custom-implementation
@@ -9,14 +9,14 @@ model-index:
9
  results:
10
  - metrics:
11
  - type: mean_reward
12
- value: 0.00 +/- 0.00
13
  name: mean_reward
14
  task:
15
  type: reinforcement-learning
16
  name: reinforcement-learning
17
  dataset:
18
- name: Taxi-v3-4x4-no_slippery
19
- type: Taxi-v3-4x4-no_slippery
20
  ---
21
 
22
  # **Q-Learning** Agent playing **Taxi-v3**
 
1
  ---
2
  tags:
3
+ - Taxi-v3
4
  - q-learning
5
  - reinforcement-learning
6
  - custom-implementation
 
9
  results:
10
  - metrics:
11
  - type: mean_reward
12
+ value: 7.54 +/- 2.74
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**
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f984033a61afc66d332c5fd97b03885ce5d3d96791c8a6f09f2425c82f60045b
3
- size 36456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe2f2383580a40fc61ea8708cdb6179d030f51ed1f5e8b33229d3110840f1a15
3
+ size 106326
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "Taxi-v3", "mean_reward": 0.0, "n_eval_episodes": 100, "eval_datetime": "2022-07-06T14:40:16.011386"}
 
1
+ {"env_id": "Taxi-v3", "mean_reward": 7.54, "n_eval_episodes": 100, "eval_datetime": "2022-07-06T14:41:32.864936"}