jackoyoungblood commited on
Commit
dbfa02e
1 Parent(s): 793e625

Reinforce-PongPolGrad-2200 training episodes

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
@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zst 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
  *.zst 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 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - CartPole-v1
4
+ - reinforce
5
+ - reinforcement-learning
6
+ - custom-implementation
7
+ - deep-rl-class
8
+ model-index:
9
+ - name: Reinforce-PongPolicyGradient
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: CartPole-v1
16
+ type: CartPole-v1
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 9.38 +/- 0.62
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **Reinforce** Agent playing **CartPole-v1**
25
+ This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
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": 2200, "n_evaluation_episodes": 13, "max_t": 5000, "gamma": 0.96, "lr": 0.1, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fd52b3f849488df92070f4ccc83e1fdce79fd015dc50413ca406876558efd2e
3
+ size 3935
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:615a8cd629d0ac2456597c0f3938820d8b37931db4c8eb3823cccd49436ee0b3
3
+ size 3197
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"env_id": "CartPole-v1", "mean_reward": 9.384615384615385, "n_evaluation_episodes": 13, "eval_datetime": "2022-08-28T17:35:31.638934"}