btsas commited on
Commit
00f4b7c
1 Parent(s): 1679cd8

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
@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zstandard filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zstandard filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
32
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - Pixelcopter-PLE-v0
4
+ - reinforce
5
+ - reinforcement-learning
6
+ - custom-implementation
7
+ - deep-rl-class
8
+ model-index:
9
+ - name: Reinforce-pixelcopter
10
+ results:
11
+ - metrics:
12
+ - type: mean_reward
13
+ value: 16.40 +/- 11.94
14
+ name: mean_reward
15
+ task:
16
+ type: reinforcement-learning
17
+ name: reinforcement-learning
18
+ dataset:
19
+ name: Pixelcopter-PLE-v0
20
+ type: Pixelcopter-PLE-v0
21
+ ---
22
+
23
+ # **Reinforce** Agent playing **Pixelcopter-PLE-v0**
24
+ This is a trained model of a **Reinforce** agent playing **Pixelcopter-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": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36dee62483fb5e3b12c280eb4fbdf276b2232bc845f6e7bf61911c1b13715e38
3
+ size 4703
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70e2c36f7bc58cb2524c4c36da2bb93c5673e4a2eeb0392cdbac9f55cb38c30
3
+ size 14521
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.4, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-07T08:02:49.574910"}