sun1638650145 commited on
Commit
8991006
1 Parent(s): f8d9308

Push Reinforce agent to the Hub

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. README.md +26 -0
  3. hyperparameters.json +1 -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 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-PLE-v0
10
+ results:
11
+ - metrics:
12
+ - type: mean_reward
13
+ value: 13.30 +/- 9.12
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
+ # 使用**Reinforce**智能体来玩**Pixelcopter-PLE-v0**
24
+ 这是一个使用**Reinforce**训练有素的模型玩**Pixelcopter-PLE-v0**.
25
+ 要学习使用这个模型并训练你的模型, 请查阅深度强化学习课程第5单元: 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}
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4afb6506fe8ba007c1194555d481a4a0476bdf2b5d18877f9c122eb5101d7a93
3
+ size 15949
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"env_id": "Pixelcopter-PLE-v0", "mean_reward": 13.3, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-12T15:06:34.899809"}