Maxime Chevalier-Boisvert
|
8518802414
Made renderer import lazy to avoid PyQT dependency.
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
ce9f07ff8f
Added memory environment created by Dima.
|
7 anos atrás |
Lucas Willems
|
f1a701537a
Unlock pickup environment (#21)
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
453fff9436
Renamed standalone.py to manual_control.py
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
ed9c2e7f75
Minor fix to speed up tests
|
7 anos atrás |
Lucas Willems
|
afb32770de
Screenshots for some environments (#22)
|
7 anos atrás |
Lucas Willems
|
2a3c7dc685
Unlock (#20)
|
7 anos atrás |
Lucas Willems
|
dab3839453
Obstructed maze environment (#19)
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
3755f0c404
Update README.md
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
da3cfdec95
Update README.md
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
475adf182c
Added BlockedUnlockPickup environment
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
09bc79e364
Merge branch 'master' of github.com:maximecb/gym-minigrid
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
b2fd115e97
Added KeyCorridor environment
|
7 anos atrás |
saleml
|
341c80acd7
allow checking if a grid contains an object defined by a pair (None, object name) (#18)
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
2a4e02a576
Update README.md
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
a9653e81de
Removing pytorch_rl code because it is broken. Will update README.
|
7 anos atrás |
Lucas Willems
|
867477f48c
Increase max_steps in DoorKey to make it learnable (#15)
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
7acd1ea326
Added timeout to place_obj and place_agent
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
c53358bf8f
Fixed bug in environment string representation
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
b6ffc9ba38
Added colored floor tile the agent can walk over
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
e270e76ee5
Added object position tracking
|
7 anos atrás |
Lucas Willems
|
ea6416989f
Add `_rand_float` method (#10)
|
7 anos atrás |
Lucas Willems
|
c125ca7998
Minimum reward when success is now 0.1 (#9)
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
290ab259e4
Modified RedBlueDoor env to enforce door opening sequence
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
c99822121e
Added reward penalty based on number of time steps taken
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
636226f90e
Renamed wait action to done
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
0ad70c61dd
Added _rand_subset method to MiniGridEnv
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
40f29632c2
Added ability to render observations at any resolution
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
041225e96b
Added position randomization to RedBlueDoors env. Updated README.
|
7 anos atrás |
Maxime Chevalier-Boisvert
|
216fe87800
Merge pull request #8 from lcswillems/master
|
7 anos atrás |