pm390 commited on
Commit
88ef955
1 Parent(s): 0e5b799

Push Reinforce agent to the Hub

Browse files
Files changed (6) hide show
  1. .gitattributes +1 -0
  2. README.md +26 -0
  3. hyperparameters.json +1 -0
  4. model.pt +3 -0
  5. replay.mp4 +3 -0
  6. 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 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-01
10
+ results:
11
+ - metrics:
12
+ - type: mean_reward
13
+ value: -16.00 +/- 0.00
14
+ name: mean_reward
15
+ task:
16
+ type: reinforcement-learning
17
+ name: reinforcement-learning
18
+ dataset:
19
+ name: Pong-PLE-v0
20
+ type: Pong-PLE-v0
21
+ ---
22
+
23
+ # **Reinforce** Agent playing **Pong-PLE-v0**
24
+ This is a trained model of a **Reinforce** agent playing **Pong-PLE-v0** .
25
+ 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
26
+
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 sha256:1d334e621cb95236e75ad3a2006133b3ed09f1dd40d386c73f36636f7e1a7c83
3
+ size 39447
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a49b713c2806aedddcb1e00a0471b38b8b44ee9b6638b9b07116f6fce0525e6b
3
+ size 24281
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"env_id": "Pong-PLE-v0", "mean_reward": -16.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-05T19:49:25.369996"}