We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 7177f2c commit 77a321dCopy full SHA for 77a321d
README.md
@@ -6,14 +6,14 @@ Thanks to the author of gym-2048 https://github.com/rgal/gym-2048. The code is e
6
## Performance of environment
7
I used random policy to evaluate the performance for 1000 times. We can take random policy as a baseline.
8
9
-(1)with render:
+(1) with render:
10
average episode time:0.10279795455932617 s;
11
average step time: 0.7373 ms;
12
average highest score:106.368;
13
average total score:1078.252;
14
average steps:139.417;
15
16
-(2)without render:
+(2) without render:
17
average episode time:0.03773710775375366 s;
18
average step time: 0.2671 ms;
19
average highest score:108.24;
0 commit comments