brad commited on
Commit
a2cb19c
1 Parent(s): 39da5c4

Push Q-Learning agent to Hub

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. README.md +35 -0
  3. q-learning.pkl +0 -0
  4. replay.mp4 +3 -0
  5. results.json +1 -0
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - Taxi-v3
4
+ - q-learning
5
+ - reinforcement-learning
6
+ - custom-implementation
7
+ model-index:
8
+ - name: q-Taxi-v3
9
+ results:
10
+ - metrics:
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**
23
+ This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
24
+
25
+ ## Usage
26
+ ```python
27
+ model = load_from_hub(repo_id="brad/q-Taxi-v3", filename="q-learning.pkl")
28
+
29
+ # Don't forget to check if you need to add additional attributes (is_slippery=False etc)
30
+ env = gym.make(model["env_id"])
31
+
32
+ evaluate_agent(env, model["max_steps"], model["n_eval_episodes"], model["qtable"], model["eval_seed"])
33
+
34
+ ```
35
+
q-learning.pkl ADDED
Binary file (24.6 kB). View file
 
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aa2e30cfc12223ef5aeb7bc697870ab0cc512d7735c30bf9cb558cb2ab79821
3
+ size 105221
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-05-21T16:11:03.220754"}