Hugging Face's logo

hishamcse
/
RND-SuperMarioBros-v0

Reinforcement Learning
SuperMarioBros-v0
RND
CNN
custom-implementation
atari
Eval Results
Model card Files Community
hishamcse commited on
Commit
3f83bfd
•
1 Parent(s): 4b657b6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +37 -27
README.md CHANGED
@@ -23,32 +23,42 @@ model-index:
23
  verified: false
24
  ---
25
 
26
- # **RND with CNN** Agent playing **SuperMarioBros-v0**
27
- This is a trained model of a **RND-CNN** agent playing **SuperMarioBros-v0** .
28
- To learn to use this model and train yours check this notebook on kaggle: https://www.kaggle.com/code/syedjarullahhisham/drl-extra-personal-unit-5-rnd-super-mario-bros
29
 
30
- # HyperParameters:
31
 
32
- ```
33
- "trainmethod": "RND",
34
- "envid": "SuperMarioBros-v0",
35
- "maxstepperepisode": 18000,
36
- "learningrate": 0.0001,
37
- "numenv": 128,
38
- "numstep": 128,
39
- "gamma": 0.999,
40
- "intgamma": 0.99,
41
- "lambda": 0.95,
42
- "usegae": true,
43
- "clipgradnorm": 0.5,
44
- "entropy": 0.001,
45
- "epoch": 4,
46
- "minibatch": 4,
47
- "ppoeps": 0.1,
48
- "extcoef": 5.0,
49
- "intcoef": 1.0,
50
- "stickyaction": true,
51
- "actionprob": 0.25,
52
- "lifedone": false,
53
- "obsnormstep": 50
54
- ```
 
 
 
 
 
 
 
 
 
 
 
23
  verified: false
24
  ---
25
 
26
+ # **RND with CNN** Agent playing **SuperMarioBros-v0**
27
+ This is a trained model of a **RND-CNN** agent playing **SuperMarioBros-v0** .
28
+ To learn to use this model and train yours check this notebook on kaggle: https://www.kaggle.com/code/syedjarullahhisham/drl-extra-personal-unit-5-rnd-super-mario-bros
29
 
30
+ ## Codes
31
 
32
+ Github repos(Give a star if found useful):
33
+ * https://github.com/hishamcse/DRL-Renegades-Game-Bots
34
+ * https://github.com/hishamcse/Advanced-DRL-Renegades-Game-Bots
35
+
36
+ Kaggle Notebook:
37
+ * https://www.kaggle.com/code/syedjarullahhisham/drl-extra-personal-unit-5-rnd-super-mario-bros
38
+ * https://www.kaggle.com/code/syedjarullahhisham/drl-extra-personal-unit-5-rnd-montezuma-mario-bros
39
+
40
+ # HyperParameters:
41
+
42
+ ```
43
+ "trainmethod": "RND",
44
+ "envid": "SuperMarioBros-v0",
45
+ "maxstepperepisode": 18000,
46
+ "learningrate": 0.0001,
47
+ "numenv": 128,
48
+ "numstep": 128,
49
+ "gamma": 0.999,
50
+ "intgamma": 0.99,
51
+ "lambda": 0.95,
52
+ "usegae": true,
53
+ "clipgradnorm": 0.5,
54
+ "entropy": 0.001,
55
+ "epoch": 4,
56
+ "minibatch": 4,
57
+ "ppoeps": 0.1,
58
+ "extcoef": 5.0,
59
+ "intcoef": 1.0,
60
+ "stickyaction": true,
61
+ "actionprob": 0.25,
62
+ "lifedone": false,
63
+ "obsnormstep": 50
64
+ ```