 Maxime Chevalier-Boisvert
|
c99822121e
Added reward penalty based on number of time steps taken
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
636226f90e
Renamed wait action to done
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
146fd10741
Made reward_range the same for all environments, rewards are in [0, 1]
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
852476db7c
Finished renaming MiniGrid methods for PEP8 conformance
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
bfd0f76513
Faster visibility algorithm. Method renamings.
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
ec9e19efe7
Renamed fields to match PEP8 convention
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
3c52268b00
Progress on RoomGrid-v0 env
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
340c03a446
Cleaned up and simplified _genGrid functions
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
c4049b13ed
Added Playground-v0 environment for experiments
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
2b1d180dda
Corrected reward ranges for environments
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
25fe4664fa
Modified environments so they all produce observations in a dict
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
114caa944a
Fixes based on changes in OpenAI Gym 0.9.6
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
c46ade2f4f
Fixed bug in fetch environment
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
723359da33
Removed waitEnds flag
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
73e6d3d2f1
Made adjustments to GoToObject based on GoToDoor env
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
3d0c94f876
Removed "advice" from observations. Randomized GoToDoor room size.
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
360927639b
Added wrapper for one-hot string encoding. Fixed bugs in goto env.
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
116bfb2d4b
Completed implementation of goto env
|
6 vuotta sitten |
|
Maxime Chevalier-Boisvert
|
67acc5ff18
Started work on goto env
|
6 vuotta sitten |
