 Maxime Chevalier-Boisvert
|
7c4e96a806
Implemented flat, one-hot string encoding into observations
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
fad2fc94ee
Modified fetch env for flat encoding
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
e02777d81b
Added function to encode observations to FetchEnv
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
16698be044
Added 5x5 config for the fetch environment
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
80b3178610
Moved rl code to pytorch-rl. Fixed warnings. Fixed issue w/ flat obs.
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
c080bf08d8
Added _randPos utility function
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
f47e47272e
Added animation for door-key curriculum
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
dbecad9ad0
Added randomization to DoorKey envs
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
95448c1ebd
Added check in run_tests.py
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
25cc3b5253
Made it so agent can see what it is carrying in observations
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
5daf219a68
Added tests. Moved envs into own source files.
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
4c0fb7cf53
Update README.md
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
7edf1575f1
Update README.md
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
0d9c084e68
Merge pull request #2 from zach-nervana/master
|
%!s(int64=6) %!d(string=hai) anos |
 Zach Dwiel
|
4cfe559b0e
include environments in install
|
%!s(int64=6) %!d(string=hai) anos |
|
Zach Dwiel
|
31132832e3
update setup.py to actually install the package
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
6092631168
Updated README
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
23d1b6b98d
Added smaller DoorKey environments, exploration bonus wrapper
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
18480bfef3
Changed empty env size
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
f2824c7687
Implemented count-based exploration system (intrinsic motivation)
|
%!s(int64=6) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
c23608ec9a
Update README.md
|
%!s(int64=7) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
acaec3c75a
Added figure for empty environment
|
%!s(int64=7) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
491c79586b
Update README.md
|
%!s(int64=7) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
88cdaf172f
Update README.md
|
%!s(int64=7) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
f09e55594e
Merge branch 'master' of github.com:maximecb/gym-minigrid
|
%!s(int64=7) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
d65ae2c098
Added missing dependency
|
%!s(int64=7) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
2f9617b470
Update README.md
|
%!s(int64=7) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
63d3d94699
Implemented box object type
|
%!s(int64=7) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
594b8d25f7
Update README.md
|
%!s(int64=7) %!d(string=hai) anos |
|
Maxime Chevalier-Boisvert
|
4a8cace595
Renamed file
|
%!s(int64=7) %!d(string=hai) anos |
