 Maxime Chevalier-Boisvert
|
ca85d1086d
Added recurrent MLP policy
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
c4257fd34c
Minor change
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
780c75e2cd
RL code updates from upstream repos, removed Atari dependencies
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
21c0eaa8c7
Renamed pytorch-rl to pytorch_rl for Python importability
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
723359da33
Removed waitEnds flag
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
4267b1d39e
Completed PutNear environment
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
87a0befdbf
Added ability to drop/put down objects. Started work on PutNear env.
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
5fd284ff88
Minor refactoring for environment creation process
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
0ecec6bce9
Minor bugfix on FlatObsWrapper
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
73e6d3d2f1
Made adjustments to GoToObject based on GoToDoor env
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
3d0c94f876
Removed "advice" from observations. Randomized GoToDoor room size.
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
a99538576b
Update README.md
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
c8b35cb515
Updated README
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
ad4358543a
Added go to door environment to README
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
f2dd5adfc3
Added color names list to minigrid.py
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
1a80488ad0
Fixed bug, improved reward function in GoToDoor env
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
c75d108362
Added more configs for GoToDoor environment
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
c4f68f309b
Implemented GoToDoor environment
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
28df92e70d
Fixed issues with run_tests.py, grid encode/decode
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
e7e870ce2d
Fixed issues with wrappers
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
360927639b
Added wrapper for one-hot string encoding. Fixed bugs in goto env.
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
116bfb2d4b
Completed implementation of goto env
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
67acc5ff18
Started work on goto env
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
a05dd9456f
Split out simple_envs.py
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
d4d83a9bf6
Added warning if cuda is disabled, to avoid silent failure
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
32535cc145
Changed reward range for fetch environment
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
e02777d81b
Added function to encode observations to FetchEnv
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
16698be044
Added 5x5 config for the fetch environment
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
80b3178610
Moved rl code to pytorch-rl. Fixed warnings. Fixed issue w/ flat obs.
|
il y a 7 ans |
|
Maxime Chevalier-Boisvert
|
c080bf08d8
Added _randPos utility function
|
il y a 7 ans |
