.. |
__init__.py
|
20b9912444
Implemented distributional shift AI safety environment
|
5 gadi atpakaļ |
blockedunlockpickup.py
|
475adf182c
Added BlockedUnlockPickup environment
|
6 gadi atpakaļ |
crossing.py
|
13d4651e03
Refactored to eliminate start_pos, simplify code.
|
5 gadi atpakaļ |
distshift.py
|
13d4651e03
Refactored to eliminate start_pos, simplify code.
|
5 gadi atpakaļ |
doorkey.py
|
13d4651e03
Refactored to eliminate start_pos, simplify code.
|
5 gadi atpakaļ |
dynamicobstacles.py
|
97bca6e172
Fixed issues with dynamic obstacles env
|
5 gadi atpakaļ |
empty.py
|
13d4651e03
Refactored to eliminate start_pos, simplify code.
|
5 gadi atpakaļ |
fetch.py
|
c99822121e
Added reward penalty based on number of time steps taken
|
6 gadi atpakaļ |
fourrooms.py
|
13d4651e03
Refactored to eliminate start_pos, simplify code.
|
5 gadi atpakaļ |
gotodoor.py
|
c99822121e
Added reward penalty based on number of time steps taken
|
6 gadi atpakaļ |
gotoobject.py
|
c99822121e
Added reward penalty based on number of time steps taken
|
6 gadi atpakaļ |
keycorridor.py
|
b2fd115e97
Added KeyCorridor environment
|
6 gadi atpakaļ |
lockedroom.py
|
13d4651e03
Refactored to eliminate start_pos, simplify code.
|
5 gadi atpakaļ |
memory.py
|
13d4651e03
Refactored to eliminate start_pos, simplify code.
|
5 gadi atpakaļ |
multiroom.py
|
999599a412
Added configuration for MultiRoom env
|
5 gadi atpakaļ |
obstructedmaze.py
|
f16b7c79bc
Fixed placing key/box in same position with blocking_ball. (#58)
|
5 gadi atpakaļ |
playground_v0.py
|
146fd10741
Made reward_range the same for all environments, rewards are in [0, 1]
|
6 gadi atpakaļ |
putnear.py
|
e270e76ee5
Added object position tracking
|
6 gadi atpakaļ |
redbluedoors.py
|
051761ec21
Update redbluedoors.py
|
5 gadi atpakaļ |
unlock.py
|
2a3c7dc685
Unlock (#20)
|
6 gadi atpakaļ |
unlockpickup.py
|
afb32770de
Screenshots for some environments (#22)
|
6 gadi atpakaļ |