Skip to content

Table of environments

Marco Birck edited this page Sep 15, 2017 · 7 revisions

Here is a synopsis of the environments as of 2016-06-20, in order by space dimensionality. See discussion and code in Write more documentation about environments: Issue #106.

Environment Id Observation Space Action Space Reward Range tStepL Trials rThresh
TimePilot-ram-v0 Box(128,) Discrete(10) (-inf, inf) 10000 100 None
Amidar-ram-v0 Box(128,) Discrete(10) (-inf, inf) 10000 100 None
WizardOfWor-ram-v0 Box(128,) Discrete(10) (-inf, inf) 10000 100 None
Asteroids-ram-v0 Box(128,) Discrete(14) (-inf, inf) 10000 100 None
KungFuMaster-ram-v0 Box(128,) Discrete(14) (-inf, inf) 10000 100 None
JourneyEscape-ram-v0 Box(128,) Discrete(16) (-inf, inf) 10000 100 None
Robotank-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Berzerk-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
ChopperCommand-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
DoubleDunk-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Gravitar-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
YarsRevenge-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Krull-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
PrivateEye-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Seaquest-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Solaris-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
ElevatorAction-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Frostbite-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
BankHeist-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Venture-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Zaxxon-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Tennis-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
FishingDerby-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Kangaroo-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Alien-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
BattleZone-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
IceHockey-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Boxing-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Riverraid-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
StarGunner-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Pitfall-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
MontezumaRevenge-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Centipede-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
RoadRunner-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Jamesbond-ram-v0 Box(128,) Discrete(18) (-inf, inf) 10000 100 None
Skiing-ram-v0 Box(128,) Discrete(3) (-inf, inf) 10000 100 None
Freeway-ram-v0 Box(128,) Discrete(3) (-inf, inf) 10000 100 None
Atlantis-ram-v0 Box(128,) Discrete(4) (-inf, inf) 10000 100 None
Pooyan-ram-v0 Box(128,) Discrete(6) (-inf, inf) 10000 100 None
SpaceInvaders-ram-v0 Box(128,) Discrete(6) (-inf, inf) 10000 100 None
AirRaid-ram-v0 Box(128,) Discrete(6) (-inf, inf) 10000 100 None
Carnival-ram-v0 Box(128,) Discrete(6) (-inf, inf) 10000 100 None
Bowling-ram-v0 Box(128,) Discrete(6) (-inf, inf) 10000 100 None
DemonAttack-ram-v0 Box(128,) Discrete(6) (-inf, inf) 10000 100 None
NameThisGame-ram-v0 Box(128,) Discrete(6) (-inf, inf) 10000 100 None
Pong-ram-v0 Box(128,) Discrete(6) (-inf, inf) 10000 100 None
Breakout-ram-v0 Box(128,) Discrete(6) (-inf, inf) 10000 100 None
Qbert-ram-v0 Box(128,) Discrete(6) (-inf, inf) 10000 100 None
UpNDown-ram-v0 Box(128,) Discrete(6) (-inf, inf) 10000 100 None
Assault-ram-v0 Box(128,) Discrete(7) (-inf, inf) 10000 100 None
Phoenix-ram-v0 Box(128,) Discrete(8) (-inf, inf) 10000 100 None
Gopher-ram-v0 Box(128,) Discrete(8) (-inf, inf) 10000 100 None
Tutankham-ram-v0 Box(128,) Discrete(8) (-inf, inf) 10000 100 None
Enduro-ram-v0 Box(128,) Discrete(9) (-inf, inf) 10000 100 None
BeamRider-ram-v0 Box(128,) Discrete(9) (-inf, inf) 10000 100 None
Asterix-ram-v0 Box(128,) Discrete(9) (-inf, inf) 10000 100 None
CrazyClimber-ram-v0 Box(128,) Discrete(9) (-inf, inf) 10000 100 None
MsPacman-ram-v0 Box(128,) Discrete(9) (-inf, inf) 10000 100 None
VideoPinball-ram-v0 Box(128,) Discrete(9) (-inf, inf) 10000 100 None
MountainCar-v0 Box(2,) Discrete(3) (-inf, inf) 200 100 -110.0
CNNClassifierTraining-v0 Box(2,) Tuple(Box(1,), Box(1,), Box(1,), Box(1,), Box(1,), Box(1,), Box(5, 2), Box(2, 2)) (-inf, inf) 1000 100 None
TimePilot-v0 Box(210, 160, 3) Discrete(10) (-inf, inf) 10000 100 None
Asteroids-v0 Box(210, 160, 3) Discrete(14) (-inf, inf) 10000 100 None
KungFuMaster-v0 Box(210, 160, 3) Discrete(14) (-inf, inf) 10000 100 None
Alien-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Berzerk-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
MontezumaRevenge-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Zaxxon-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Venture-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Frostbite-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Seaquest-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Pitfall-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
ElevatorAction-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
FishingDerby-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Robotank-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Jamesbond-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
PrivateEye-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
StarGunner-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
YarsRevenge-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Boxing-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Solaris-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
BattleZone-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Gravitar-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
RoadRunner-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Krull-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Riverraid-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
ChopperCommand-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
IceHockey-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Kangaroo-v0 Box(210, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Freeway-v0 Box(210, 160, 3) Discrete(3) (-inf, inf) 10000 100 None
Atlantis-v0 Box(210, 160, 3) Discrete(4) (-inf, inf) 10000 100 None
DemonAttack-v0 Box(210, 160, 3) Discrete(6) (-inf, inf) 10000 100 None
NameThisGame-v0 Box(210, 160, 3) Discrete(6) (-inf, inf) 10000 100 None
Bowling-v0 Box(210, 160, 3) Discrete(6) (-inf, inf) 10000 100 None
Qbert-v0 Box(210, 160, 3) Discrete(6) (-inf, inf) 10000 100 None
UpNDown-v0 Box(210, 160, 3) Discrete(6) (-inf, inf) 10000 100 None
Pong-v0 Box(210, 160, 3) Discrete(6) (-inf, inf) 10000 100 None
Breakout-v0 Box(210, 160, 3) Discrete(4) (-inf, inf) 10000 100 None
SpaceInvaders-v0 Box(210, 160, 3) Discrete(6) (-inf, inf) 10000 100 None
Phoenix-v0 Box(210, 160, 3) Discrete(8) (-inf, inf) 10000 100 None
BeamRider-v0 Box(210, 160, 3) Discrete(9) (-inf, inf) 10000 100 None
Asterix-v0 Box(210, 160, 3) Discrete(9) (-inf, inf) 10000 100 None
CrazyClimber-v0 Box(210, 160, 3) Discrete(9) (-inf, inf) 10000 100 None
Enduro-v0 Box(210, 160, 3) Discrete(9) (-inf, inf) 10000 100 None
MsPacman-v0 Box(210, 160, 3) Discrete(9) (-inf, inf) 10000 100 None
JourneyEscape-v0 Box(230, 160, 3) Discrete(16) (-inf, inf) 10000 100 None
Amidar-v0 Box(250, 160, 3) Discrete(10) (-inf, inf) 10000 100 None
WizardOfWor-v0 Box(250, 160, 3) Discrete(10) (-inf, inf) 10000 100 None
DoubleDunk-v0 Box(250, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Centipede-v0 Box(250, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Tennis-v0 Box(250, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
BankHeist-v0 Box(250, 160, 3) Discrete(18) (-inf, inf) 10000 100 None
Skiing-v0 Box(250, 160, 3) Discrete(3) (-inf, inf) 10000 100 None
Carnival-v0 Box(250, 160, 3) Discrete(6) (-inf, inf) 10000 100 None
Pooyan-v0 Box(250, 160, 3) Discrete(6) (-inf, inf) 10000 100 None
AirRaid-v0 Box(250, 160, 3) Discrete(6) (-inf, inf) 10000 100 None
Assault-v0 Box(250, 160, 3) Discrete(7) (-inf, inf) 10000 100 None
Tutankham-v0 Box(250, 160, 3) Discrete(8) (-inf, inf) 10000 100 None
Gopher-v0 Box(250, 160, 3) Discrete(8) (-inf, inf) 10000 100 None
VideoPinball-v0 Box(250, 160, 3) Discrete(9) (-inf, inf) 10000 100 None
Go19x19-v0 Box(3, 19, 19) Discrete(363) (-inf, inf) 1000 100 None
Hex9x9-v0 Box(3, 9, 9) Discrete(82) (-inf, inf) 1000 100 None
Go9x9-v0 Box(3, 9, 9) Discrete(83) (-inf, inf) 1000 100 None
SemiSupervisedPendulumRandom-v0 Box(3,) Box(1,) (-inf, inf) 1000 100 None
SemiSupervisedPendulumDecay-v0 Box(3,) Box(1,) (-inf, inf) 1000 100 None
SemiSupervisedPendulumNoise-v0 Box(3,) Box(1,) (-inf, inf) 1000 100 None
Pendulum-v0 Box(3,) Box(1,) (-inf, inf) 200 100 None
CartPole-v0 Box(4,) Discrete(2) (-inf, inf) 200 100 195.0
Acrobot-v0 Box(4,) Discrete(3) (-inf, inf) 200 100 -100
InterpretabilityCartpoleObservations-v0 Box(4,) Tuple(Discrete(2), Box(4,), Box(4,), Box(4,), Box(4,), Box(4,)) (-inf, inf) 1000 100 None
InterpretabilityCartpoleActions-v0 Box(4,) Tuple(Discrete(2), Discrete(2), Discrete(2), Discrete(2), Discrete(2), Discrete(2)) (-inf, inf) 1000 100 None
DoomTakeCover-v0 Box(480, 640, 3) High-Low(2, 3) (-inf, inf) 1000 100 None
DoomDefendCenter-v0 Box(480, 640, 3) High-Low(3, 3) (-inf, inf) 1000 100 None
DoomHealthGathering-v0 Box(480, 640, 3) High-Low(3, 3) (-inf, inf) 1000 100 None
DoomPredictPosition-v0 Box(480, 640, 3) High-Low(3, 3) (-inf, inf) 1000 100 None
DoomBasic-v0 Box(480, 640, 3) High-Low(3, 3) (-inf, inf) 1000 100 None
DoomMyWayHome-v0 Box(480, 640, 3) High-Low(3, 3) (-inf, inf) 1000 100 None
DoomDefendLine-v0 Box(480, 640, 3) High-Low(3, 3) (-inf, inf) 1000 100 None
DoomDeathmatch-v0 Box(480, 640, 3) High-Low(44, 3) (-inf, inf) 1000 100 None
DoomCorridor-v0 Box(480, 640, 3) High-Low(6, 3) (-inf, inf) 1000 100 None
ConvergenceControl-v0 Box(6,) Tuple(Box(1,), Box(1,), Box(1,), Box(1,), Box(1,), Box(1,)) (-inf, inf) 1000 100 None
OneRoundNondeterministicReward-v0 Discrete(1) Discrete(2) (-inf, inf) 1000 100 None
OneRoundDeterministicReward-v0 Discrete(1) Discrete(2) (-inf, inf) 1000 100 None
Roulette-v0 Discrete(1) Discrete(38) (-inf, inf) 100 100 None
FrozenLake-v0 Discrete(16) Discrete(4) (-inf, inf) 100 100 0.78
TwoRoundDeterministicReward-v0 Discrete(3) Discrete(2) (-inf, inf) 1000 100 None
TwoRoundNondeterministicReward-v0 Discrete(3) Discrete(2) (-inf, inf) 1000 100 None
Reverse-v0 Discrete(3) Tuple(Discrete(2), Discrete(2), Discrete(2)) (-inf, inf) 200 100 25.0
ReversedAddition-v0 Discrete(4) Tuple(Discrete(4), Discrete(2), Discrete(3)) (-inf, inf) 200 100 25.0
ReversedAddition3-v0 Discrete(4) Tuple(Discrete(4), Discrete(2), Discrete(3)) (-inf, inf) 200 100 25.0
NChain-v0 Discrete(5) Discrete(2) (-inf, inf) 1000 100 None
Taxi-v1 Discrete(500) Discrete(6) (-inf, inf) 200 100 9.7
Copy-v0 Discrete(6) Tuple(Discrete(2), Discrete(2), Discrete(5)) (-inf, inf) 200 100 25.0
RepeatCopy-v0 Discrete(6) Tuple(Discrete(2), Discrete(2), Discrete(5)) (-inf, inf) 200 100 75.0
DuplicatedInput-v0 Discrete(6) Tuple(Discrete(2), Discrete(2), Discrete(5)) (-inf, inf) 200 100 9.0
FrozenLake8x8-v0 Discrete(64) Discrete(4) (-inf, inf) 200 100 0.99
OffSwitchCartpole-v0 Tuple(Discrete(2), Box(4,)) Discrete(2) (-inf, inf) 1000 100 None
Blackjack-v0 Tuple(Discrete(32), Discrete(11), Discrete(2)) Discrete(2) (-inf, inf) 1000 100 None