akanametov commited on
Commit
255c291
1 Parent(s): 6a9c897

Push Reinforce agent to the Hub

Browse files
Files changed (6) hide show
  1. .gitattributes +1 -0
  2. README.md +27 -0
  3. hyperparameters.json +1 -0
  4. model.pt +3 -0
  5. replay.mp4 +3 -0
  6. results.json +1 -0
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - Pong-PLE-v0
4
+ - reinforce
5
+ - reinforcement-learning
6
+ - custom-implementation
7
+ - deep-rl-class
8
+ model-index:
9
+ - name: Reinforce-Pong-PLE-v0
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: Pong-PLE-v0
16
+ type: Pong-PLE-v0
17
+ metrics:
18
+ - type: mean_reward
19
+ value: -16.00 +/- 0.00
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **Reinforce** Agent playing **Pong-PLE-v0**
25
+ This is a trained model of a **Reinforce** agent playing **Pong-PLE-v0** .
26
+ To learn to use this model and train yours check Unit 5 of the Deep Reinforcement Learning Class: https://github.com/huggingface/deep-rl-class/tree/main/unit5
27
+
hyperparameters.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"h_size": 64, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 5000, "gamma": 0.99, "lr": 0.01, "env_id": "Pong-PLE-v0", "state_space": 7, "action_space": 3}
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74ed932a71662cc62f14a37154f12b8fdfc91809df9b8d05920ce7a6c3aa2315
3
+ size 39495
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b11d2e946bb9778e3985c25a7eaf8b241156e2217b6d5abef09917912293d714
3
+ size 29420
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"env_id": "Pong-PLE-v0", "mean_reward": -16.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-28T06:34:01.211022"}