epsil commited on
Commit
956f90a
1 Parent(s): 370edc3

Push Reinforce agent to the Hub

Browse files
Files changed (6) hide show
  1. .gitattributes +1 -0
  2. README.md +25 -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 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - CartPole-v1
4
+ - reinforce
5
+ - reinforcement-learning
6
+ - custom-implementation
7
+ - deep-rl-class
8
+ model-index:
9
+ - name: Reinforce-cartpole
10
+ results:
11
+ - metrics:
12
+ - type: mean_reward
13
+ value: 500.00 +/- 0.00
14
+ name: mean_reward
15
+ task:
16
+ type: reinforcement-learning
17
+ name: reinforcement-learning
18
+ dataset:
19
+ name: CartPole-v1
20
+ type: CartPole-v1
21
+ ---
22
+
23
+ # **Reinforce** Agent playing **CartPole-v1**
24
+ This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
25
+
hyperparameters.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "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:f9a6235570024454b73d0b4be741ef90f90b050bad2941d777f43bb77a670804
3
+ size 2527
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a1f2c3a365b45555ace9974ecedf18ab0020846d85448d3c28ca9aafb282256
3
+ size 51084
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"env_id": "CartPole-v1", "mean_reward": 500.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-03T15:07:58.652439"}