Skip to content

Reinforcement learning agents trying to master the OpenAI universe

License

Notifications You must be signed in to change notification settings

FragLegs/grayskull

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Grayskull

Grayskull is a project for reinforcement learning agents trying to master the OpenAI universe.

Installing

Start by installing gym and universe from the github source (in a virtualenv, of course). It may take a few tries to get all of the dependencies installed.

Then, you can install grayskull by cloning this repo and calling pip install . in the root directory.

Usage

Grayskull allows you to train an RL agent on any game in OpenAI Gym or OpenAI Universe (not yet implemented) with the train.py script. All command line options are viewable by running python train.py -h. That information is also reproduced here:

usage: train.py [-h] [-g GAME] [-a {random,linear_guessing}]
                [--agent-args AGENT_ARGS] [-e EPISODES] [-r] [--monitor]
                [--seed SEED] [-v {DEBUG,INFO,WARNING,ERROR}]

Train an agent on a game

optional arguments:
  -h, --help            show this help message and exit
  -g GAME, --game GAME  Which game to train on (default: CartPole-v0)
  -a {random,linear_guessing}, --agent {random,linear_guessing}
                        Which agent to use (default: random)
  --agent-args AGENT_ARGS
                        Additional args to pass to the agent (default: {})
  -e EPISODES, --episodes EPISODES
                        How many episodes to run (-1 means run forever)
                        (default: -1)
  -r, --render          Whether to render the screen (default: False)
  --monitor             Record video and stats (default: False)
  --seed SEED           Set the random seed (default: None)
  -v {DEBUG,INFO,WARNING,ERROR}, --verbosity {DEBUG,INFO,WARNING,ERROR}
                        Verbosity level (default: INFO)

Available Agents

Available agents and their descriptions can be viewed by running python agents.py. That information is also reproduced here:

linear_guessing:

    Generates 10000 random settings for a linear params's weights and
    choose the best (where "best" is defined as the configuration that
    leads to the highest per-episode reward).

    See: https://openai.com/requests-for-research/#cartpole

linear_hill:

    Start with a random setting of the parameters, add a small amount of noise
    to the parameters, and evaluate the new parameter configuration. If it
    performs better than the old configuration, discard the old configuration
    and accept the new one.

    See: https://openai.com/requests-for-research/#cartpole

random:

    Chooses a random action at every step.

Available Games

Currently, all of the games in gym are supported (although currently only CartPole-v0 has been tested). You can list them by calling python games.py. That information is also reproduced here:

Acrobot-v1
AirRaid-ram-v0
AirRaid-ram-v3
AirRaid-ramDeterministic-v0
AirRaid-ramDeterministic-v3
AirRaid-ramNoFrameskip-v0
AirRaid-ramNoFrameskip-v3
AirRaid-v0
AirRaid-v3
AirRaidDeterministic-v0
AirRaidDeterministic-v3
AirRaidNoFrameskip-v0
AirRaidNoFrameskip-v3
Alien-ram-v0
Alien-ram-v3
Alien-ramDeterministic-v0
Alien-ramDeterministic-v3
Alien-ramNoFrameskip-v0
Alien-ramNoFrameskip-v3
Alien-v0
Alien-v3
AlienDeterministic-v0
AlienDeterministic-v3
AlienNoFrameskip-v0
AlienNoFrameskip-v3
Amidar-ram-v0
Amidar-ram-v3
Amidar-ramDeterministic-v0
Amidar-ramDeterministic-v3
Amidar-ramNoFrameskip-v0
Amidar-ramNoFrameskip-v3
Amidar-v0
Amidar-v3
AmidarDeterministic-v0
AmidarDeterministic-v3
AmidarNoFrameskip-v0
AmidarNoFrameskip-v3
Ant-v1
Assault-ram-v0
Assault-ram-v3
Assault-ramDeterministic-v0
Assault-ramDeterministic-v3
Assault-ramNoFrameskip-v0
Assault-ramNoFrameskip-v3
Assault-v0
Assault-v3
AssaultDeterministic-v0
AssaultDeterministic-v3
AssaultNoFrameskip-v0
AssaultNoFrameskip-v3
Asterix-ram-v0
Asterix-ram-v3
Asterix-ramDeterministic-v0
Asterix-ramDeterministic-v3
Asterix-ramNoFrameskip-v0
Asterix-ramNoFrameskip-v3
Asterix-v0
Asterix-v3
AsterixDeterministic-v0
AsterixDeterministic-v3
AsterixNoFrameskip-v0
AsterixNoFrameskip-v3
Asteroids-ram-v0
Asteroids-ram-v3
Asteroids-ramDeterministic-v0
Asteroids-ramDeterministic-v3
Asteroids-ramNoFrameskip-v0
Asteroids-ramNoFrameskip-v3
Asteroids-v0
Asteroids-v3
AsteroidsDeterministic-v0
AsteroidsDeterministic-v3
AsteroidsNoFrameskip-v0
AsteroidsNoFrameskip-v3
Atlantis-ram-v0
Atlantis-ram-v3
Atlantis-ramDeterministic-v0
Atlantis-ramDeterministic-v3
Atlantis-ramNoFrameskip-v0
Atlantis-ramNoFrameskip-v3
Atlantis-v0
Atlantis-v3
AtlantisDeterministic-v0
AtlantisDeterministic-v3
AtlantisNoFrameskip-v0
AtlantisNoFrameskip-v3
BankHeist-ram-v0
BankHeist-ram-v3
BankHeist-ramDeterministic-v0
BankHeist-ramDeterministic-v3
BankHeist-ramNoFrameskip-v0
BankHeist-ramNoFrameskip-v3
BankHeist-v0
BankHeist-v3
BankHeistDeterministic-v0
BankHeistDeterministic-v3
BankHeistNoFrameskip-v0
BankHeistNoFrameskip-v3
BattleZone-ram-v0
BattleZone-ram-v3
BattleZone-ramDeterministic-v0
BattleZone-ramDeterministic-v3
BattleZone-ramNoFrameskip-v0
BattleZone-ramNoFrameskip-v3
BattleZone-v0
BattleZone-v3
BattleZoneDeterministic-v0
BattleZoneDeterministic-v3
BattleZoneNoFrameskip-v0
BattleZoneNoFrameskip-v3
BeamRider-ram-v0
BeamRider-ram-v3
BeamRider-ramDeterministic-v0
BeamRider-ramDeterministic-v3
BeamRider-ramNoFrameskip-v0
BeamRider-ramNoFrameskip-v3
BeamRider-v0
BeamRider-v3
BeamRiderDeterministic-v0
BeamRiderDeterministic-v3
BeamRiderNoFrameskip-v0
BeamRiderNoFrameskip-v3
Berzerk-ram-v0
Berzerk-ram-v3
Berzerk-ramDeterministic-v0
Berzerk-ramDeterministic-v3
Berzerk-ramNoFrameskip-v0
Berzerk-ramNoFrameskip-v3
Berzerk-v0
Berzerk-v3
BerzerkDeterministic-v0
BerzerkDeterministic-v3
BerzerkNoFrameskip-v0
BerzerkNoFrameskip-v3
BipedalWalker-v2
BipedalWalkerHardcore-v2
Blackjack-v0
Bowling-ram-v0
Bowling-ram-v3
Bowling-ramDeterministic-v0
Bowling-ramDeterministic-v3
Bowling-ramNoFrameskip-v0
Bowling-ramNoFrameskip-v3
Bowling-v0
Bowling-v3
BowlingDeterministic-v0
BowlingDeterministic-v3
BowlingNoFrameskip-v0
BowlingNoFrameskip-v3
Boxing-ram-v0
Boxing-ram-v3
Boxing-ramDeterministic-v0
Boxing-ramDeterministic-v3
Boxing-ramNoFrameskip-v0
Boxing-ramNoFrameskip-v3
Boxing-v0
Boxing-v3
BoxingDeterministic-v0
BoxingDeterministic-v3
BoxingNoFrameskip-v0
BoxingNoFrameskip-v3
Breakout-ram-v0
Breakout-ram-v3
Breakout-ramDeterministic-v0
Breakout-ramDeterministic-v3
Breakout-ramNoFrameskip-v0
Breakout-ramNoFrameskip-v3
Breakout-v0
Breakout-v3
BreakoutDeterministic-v0
BreakoutDeterministic-v3
BreakoutNoFrameskip-v0
BreakoutNoFrameskip-v3
CNNClassifierTraining-v0
CarRacing-v0
Carnival-ram-v0
Carnival-ram-v3
Carnival-ramDeterministic-v0
Carnival-ramDeterministic-v3
Carnival-ramNoFrameskip-v0
Carnival-ramNoFrameskip-v3
Carnival-v0
Carnival-v3
CarnivalDeterministic-v0
CarnivalDeterministic-v3
CarnivalNoFrameskip-v0
CarnivalNoFrameskip-v3
CartPole-v0
CartPole-v1
Centipede-ram-v0
Centipede-ram-v3
Centipede-ramDeterministic-v0
Centipede-ramDeterministic-v3
Centipede-ramNoFrameskip-v0
Centipede-ramNoFrameskip-v3
Centipede-v0
Centipede-v3
CentipedeDeterministic-v0
CentipedeDeterministic-v3
CentipedeNoFrameskip-v0
CentipedeNoFrameskip-v3
ChopperCommand-ram-v0
ChopperCommand-ram-v3
ChopperCommand-ramDeterministic-v0
ChopperCommand-ramDeterministic-v3
ChopperCommand-ramNoFrameskip-v0
ChopperCommand-ramNoFrameskip-v3
ChopperCommand-v0
ChopperCommand-v3
ChopperCommandDeterministic-v0
ChopperCommandDeterministic-v3
ChopperCommandNoFrameskip-v0
ChopperCommandNoFrameskip-v3
ConvergenceControl-v0
Copy-v0
CrazyClimber-ram-v0
CrazyClimber-ram-v3
CrazyClimber-ramDeterministic-v0
CrazyClimber-ramDeterministic-v3
CrazyClimber-ramNoFrameskip-v0
CrazyClimber-ramNoFrameskip-v3
CrazyClimber-v0
CrazyClimber-v3
CrazyClimberDeterministic-v0
CrazyClimberDeterministic-v3
CrazyClimberNoFrameskip-v0
CrazyClimberNoFrameskip-v3
DemonAttack-ram-v0
DemonAttack-ram-v3
DemonAttack-ramDeterministic-v0
DemonAttack-ramDeterministic-v3
DemonAttack-ramNoFrameskip-v0
DemonAttack-ramNoFrameskip-v3
DemonAttack-v0
DemonAttack-v3
DemonAttackDeterministic-v0
DemonAttackDeterministic-v3
DemonAttackNoFrameskip-v0
DemonAttackNoFrameskip-v3
DoubleDunk-ram-v0
DoubleDunk-ram-v3
DoubleDunk-ramDeterministic-v0
DoubleDunk-ramDeterministic-v3
DoubleDunk-ramNoFrameskip-v0
DoubleDunk-ramNoFrameskip-v3
DoubleDunk-v0
DoubleDunk-v3
DoubleDunkDeterministic-v0
DoubleDunkDeterministic-v3
DoubleDunkNoFrameskip-v0
DoubleDunkNoFrameskip-v3
DuplicatedInput-v0
ElevatorAction-ram-v0
ElevatorAction-ram-v3
ElevatorAction-ramDeterministic-v0
ElevatorAction-ramDeterministic-v3
ElevatorAction-ramNoFrameskip-v0
ElevatorAction-ramNoFrameskip-v3
ElevatorAction-v0
ElevatorAction-v3
ElevatorActionDeterministic-v0
ElevatorActionDeterministic-v3
ElevatorActionNoFrameskip-v0
ElevatorActionNoFrameskip-v3
Enduro-ram-v0
Enduro-ram-v3
Enduro-ramDeterministic-v0
Enduro-ramDeterministic-v3
Enduro-ramNoFrameskip-v0
Enduro-ramNoFrameskip-v3
Enduro-v0
Enduro-v3
EnduroDeterministic-v0
EnduroDeterministic-v3
EnduroNoFrameskip-v0
EnduroNoFrameskip-v3
FishingDerby-ram-v0
FishingDerby-ram-v3
FishingDerby-ramDeterministic-v0
FishingDerby-ramDeterministic-v3
FishingDerby-ramNoFrameskip-v0
FishingDerby-ramNoFrameskip-v3
FishingDerby-v0
FishingDerby-v3
FishingDerbyDeterministic-v0
FishingDerbyDeterministic-v3
FishingDerbyNoFrameskip-v0
FishingDerbyNoFrameskip-v3
Freeway-ram-v0
Freeway-ram-v3
Freeway-ramDeterministic-v0
Freeway-ramDeterministic-v3
Freeway-ramNoFrameskip-v0
Freeway-ramNoFrameskip-v3
Freeway-v0
Freeway-v3
FreewayDeterministic-v0
FreewayDeterministic-v3
FreewayNoFrameskip-v0
FreewayNoFrameskip-v3
Frostbite-ram-v0
Frostbite-ram-v3
Frostbite-ramDeterministic-v0
Frostbite-ramDeterministic-v3
Frostbite-ramNoFrameskip-v0
Frostbite-ramNoFrameskip-v3
Frostbite-v0
Frostbite-v3
FrostbiteDeterministic-v0
FrostbiteDeterministic-v3
FrostbiteNoFrameskip-v0
FrostbiteNoFrameskip-v3
FrozenLake-v0
FrozenLake8x8-v0
Go19x19-v0
Go9x9-v0
Gopher-ram-v0
Gopher-ram-v3
Gopher-ramDeterministic-v0
Gopher-ramDeterministic-v3
Gopher-ramNoFrameskip-v0
Gopher-ramNoFrameskip-v3
Gopher-v0
Gopher-v3
GopherDeterministic-v0
GopherDeterministic-v3
GopherNoFrameskip-v0
GopherNoFrameskip-v3
Gravitar-ram-v0
Gravitar-ram-v3
Gravitar-ramDeterministic-v0
Gravitar-ramDeterministic-v3
Gravitar-ramNoFrameskip-v0
Gravitar-ramNoFrameskip-v3
Gravitar-v0
Gravitar-v3
GravitarDeterministic-v0
GravitarDeterministic-v3
GravitarNoFrameskip-v0
GravitarNoFrameskip-v3
GuessingGame-v0
HalfCheetah-v1
Hex9x9-v0
Hopper-v1
HotterColder-v0
Humanoid-v1
HumanoidStandup-v1
IceHockey-ram-v0
IceHockey-ram-v3
IceHockey-ramDeterministic-v0
IceHockey-ramDeterministic-v3
IceHockey-ramNoFrameskip-v0
IceHockey-ramNoFrameskip-v3
IceHockey-v0
IceHockey-v3
IceHockeyDeterministic-v0
IceHockeyDeterministic-v3
IceHockeyNoFrameskip-v0
IceHockeyNoFrameskip-v3
InvertedDoublePendulum-v1
InvertedPendulum-v1
Jamesbond-ram-v0
Jamesbond-ram-v3
Jamesbond-ramDeterministic-v0
Jamesbond-ramDeterministic-v3
Jamesbond-ramNoFrameskip-v0
Jamesbond-ramNoFrameskip-v3
Jamesbond-v0
Jamesbond-v3
JamesbondDeterministic-v0
JamesbondDeterministic-v3
JamesbondNoFrameskip-v0
JamesbondNoFrameskip-v3
JourneyEscape-ram-v0
JourneyEscape-ram-v3
JourneyEscape-ramDeterministic-v0
JourneyEscape-ramDeterministic-v3
JourneyEscape-ramNoFrameskip-v0
JourneyEscape-ramNoFrameskip-v3
JourneyEscape-v0
JourneyEscape-v3
JourneyEscapeDeterministic-v0
JourneyEscapeDeterministic-v3
JourneyEscapeNoFrameskip-v0
JourneyEscapeNoFrameskip-v3
Kangaroo-ram-v0
Kangaroo-ram-v3
Kangaroo-ramDeterministic-v0
Kangaroo-ramDeterministic-v3
Kangaroo-ramNoFrameskip-v0
Kangaroo-ramNoFrameskip-v3
Kangaroo-v0
Kangaroo-v3
KangarooDeterministic-v0
KangarooDeterministic-v3
KangarooNoFrameskip-v0
KangarooNoFrameskip-v3
Krull-ram-v0
Krull-ram-v3
Krull-ramDeterministic-v0
Krull-ramDeterministic-v3
Krull-ramNoFrameskip-v0
Krull-ramNoFrameskip-v3
Krull-v0
Krull-v3
KrullDeterministic-v0
KrullDeterministic-v3
KrullNoFrameskip-v0
KrullNoFrameskip-v3
KungFuMaster-ram-v0
KungFuMaster-ram-v3
KungFuMaster-ramDeterministic-v0
KungFuMaster-ramDeterministic-v3
KungFuMaster-ramNoFrameskip-v0
KungFuMaster-ramNoFrameskip-v3
KungFuMaster-v0
KungFuMaster-v3
KungFuMasterDeterministic-v0
KungFuMasterDeterministic-v3
KungFuMasterNoFrameskip-v0
KungFuMasterNoFrameskip-v3
LunarLander-v2
LunarLanderContinuous-v2
MontezumaRevenge-ram-v0
MontezumaRevenge-ram-v3
MontezumaRevenge-ramDeterministic-v0
MontezumaRevenge-ramDeterministic-v3
MontezumaRevenge-ramNoFrameskip-v0
MontezumaRevenge-ramNoFrameskip-v3
MontezumaRevenge-v0
MontezumaRevenge-v3
MontezumaRevengeDeterministic-v0
MontezumaRevengeDeterministic-v3
MontezumaRevengeNoFrameskip-v0
MontezumaRevengeNoFrameskip-v3
MountainCar-v0
MountainCarContinuous-v0
MsPacman-ram-v0
MsPacman-ram-v3
MsPacman-ramDeterministic-v0
MsPacman-ramDeterministic-v3
MsPacman-ramNoFrameskip-v0
MsPacman-ramNoFrameskip-v3
MsPacman-v0
MsPacman-v3
MsPacmanDeterministic-v0
MsPacmanDeterministic-v3
MsPacmanNoFrameskip-v0
MsPacmanNoFrameskip-v3
NChain-v0
NameThisGame-ram-v0
NameThisGame-ram-v3
NameThisGame-ramDeterministic-v0
NameThisGame-ramDeterministic-v3
NameThisGame-ramNoFrameskip-v0
NameThisGame-ramNoFrameskip-v3
NameThisGame-v0
NameThisGame-v3
NameThisGameDeterministic-v0
NameThisGameDeterministic-v3
NameThisGameNoFrameskip-v0
NameThisGameNoFrameskip-v3
OffSwitchCartpole-v0
OffSwitchCartpoleProb-v0
OneRoundDeterministicReward-v0
OneRoundNondeterministicReward-v0
Pendulum-v0
Phoenix-ram-v0
Phoenix-ram-v3
Phoenix-ramDeterministic-v0
Phoenix-ramDeterministic-v3
Phoenix-ramNoFrameskip-v0
Phoenix-ramNoFrameskip-v3
Phoenix-v0
Phoenix-v3
PhoenixDeterministic-v0
PhoenixDeterministic-v3
PhoenixNoFrameskip-v0
PhoenixNoFrameskip-v3
Pitfall-ram-v0
Pitfall-ram-v3
Pitfall-ramDeterministic-v0
Pitfall-ramDeterministic-v3
Pitfall-ramNoFrameskip-v0
Pitfall-ramNoFrameskip-v3
Pitfall-v0
Pitfall-v3
PitfallDeterministic-v0
PitfallDeterministic-v3
PitfallNoFrameskip-v0
PitfallNoFrameskip-v3
Pong-ram-v0
Pong-ram-v3
Pong-ramDeterministic-v0
Pong-ramDeterministic-v3
Pong-ramNoFrameskip-v0
Pong-ramNoFrameskip-v3
Pong-v0
Pong-v3
PongDeterministic-v0
PongDeterministic-v3
PongNoFrameskip-v0
PongNoFrameskip-v3
Pooyan-ram-v0
Pooyan-ram-v3
Pooyan-ramDeterministic-v0
Pooyan-ramDeterministic-v3
Pooyan-ramNoFrameskip-v0
Pooyan-ramNoFrameskip-v3
Pooyan-v0
Pooyan-v3
PooyanDeterministic-v0
PooyanDeterministic-v3
PooyanNoFrameskip-v0
PooyanNoFrameskip-v3
PredictActionsCartpole-v0
PredictObsCartpole-v0
PrivateEye-ram-v0
PrivateEye-ram-v3
PrivateEye-ramDeterministic-v0
PrivateEye-ramDeterministic-v3
PrivateEye-ramNoFrameskip-v0
PrivateEye-ramNoFrameskip-v3
PrivateEye-v0
PrivateEye-v3
PrivateEyeDeterministic-v0
PrivateEyeDeterministic-v3
PrivateEyeNoFrameskip-v0
PrivateEyeNoFrameskip-v3
Qbert-ram-v0
Qbert-ram-v3
Qbert-ramDeterministic-v0
Qbert-ramDeterministic-v3
Qbert-ramNoFrameskip-v0
Qbert-ramNoFrameskip-v3
Qbert-v0
Qbert-v3
QbertDeterministic-v0
QbertDeterministic-v3
QbertNoFrameskip-v0
QbertNoFrameskip-v3
Reacher-v1
RepeatCopy-v0
Reverse-v0
ReversedAddition-v0
ReversedAddition3-v0
Riverraid-ram-v0
Riverraid-ram-v3
Riverraid-ramDeterministic-v0
Riverraid-ramDeterministic-v3
Riverraid-ramNoFrameskip-v0
Riverraid-ramNoFrameskip-v3
Riverraid-v0
Riverraid-v3
RiverraidDeterministic-v0
RiverraidDeterministic-v3
RiverraidNoFrameskip-v0
RiverraidNoFrameskip-v3
RoadRunner-ram-v0
RoadRunner-ram-v3
RoadRunner-ramDeterministic-v0
RoadRunner-ramDeterministic-v3
RoadRunner-ramNoFrameskip-v0
RoadRunner-ramNoFrameskip-v3
RoadRunner-v0
RoadRunner-v3
RoadRunnerDeterministic-v0
RoadRunnerDeterministic-v3
RoadRunnerNoFrameskip-v0
RoadRunnerNoFrameskip-v3
Robotank-ram-v0
Robotank-ram-v3
Robotank-ramDeterministic-v0
Robotank-ramDeterministic-v3
Robotank-ramNoFrameskip-v0
Robotank-ramNoFrameskip-v3
Robotank-v0
Robotank-v3
RobotankDeterministic-v0
RobotankDeterministic-v3
RobotankNoFrameskip-v0
RobotankNoFrameskip-v3
Roulette-v0
Seaquest-ram-v0
Seaquest-ram-v3
Seaquest-ramDeterministic-v0
Seaquest-ramDeterministic-v3
Seaquest-ramNoFrameskip-v0
Seaquest-ramNoFrameskip-v3
Seaquest-v0
Seaquest-v3
SeaquestDeterministic-v0
SeaquestDeterministic-v3
SeaquestNoFrameskip-v0
SeaquestNoFrameskip-v3
SemisuperPendulumDecay-v0
SemisuperPendulumNoise-v0
SemisuperPendulumRandom-v0
Skiing-ram-v0
Skiing-ram-v3
Skiing-ramDeterministic-v0
Skiing-ramDeterministic-v3
Skiing-ramNoFrameskip-v0
Skiing-ramNoFrameskip-v3
Skiing-v0
Skiing-v3
SkiingDeterministic-v0
SkiingDeterministic-v3
SkiingNoFrameskip-v0
SkiingNoFrameskip-v3
Solaris-ram-v0
Solaris-ram-v3
Solaris-ramDeterministic-v0
Solaris-ramDeterministic-v3
Solaris-ramNoFrameskip-v0
Solaris-ramNoFrameskip-v3
Solaris-v0
Solaris-v3
SolarisDeterministic-v0
SolarisDeterministic-v3
SolarisNoFrameskip-v0
SolarisNoFrameskip-v3
SpaceInvaders-ram-v0
SpaceInvaders-ram-v3
SpaceInvaders-ramDeterministic-v0
SpaceInvaders-ramDeterministic-v3
SpaceInvaders-ramNoFrameskip-v0
SpaceInvaders-ramNoFrameskip-v3
SpaceInvaders-v0
SpaceInvaders-v3
SpaceInvadersDeterministic-v0
SpaceInvadersDeterministic-v3
SpaceInvadersNoFrameskip-v0
SpaceInvadersNoFrameskip-v3
StarGunner-ram-v0
StarGunner-ram-v3
StarGunner-ramDeterministic-v0
StarGunner-ramDeterministic-v3
StarGunner-ramNoFrameskip-v0
StarGunner-ramNoFrameskip-v3
StarGunner-v0
StarGunner-v3
StarGunnerDeterministic-v0
StarGunnerDeterministic-v3
StarGunnerNoFrameskip-v0
StarGunnerNoFrameskip-v3
Swimmer-v1
Taxi-v1
Tennis-ram-v0
Tennis-ram-v3
Tennis-ramDeterministic-v0
Tennis-ramDeterministic-v3
Tennis-ramNoFrameskip-v0
Tennis-ramNoFrameskip-v3
Tennis-v0
Tennis-v3
TennisDeterministic-v0
TennisDeterministic-v3
TennisNoFrameskip-v0
TennisNoFrameskip-v3
TimePilot-ram-v0
TimePilot-ram-v3
TimePilot-ramDeterministic-v0
TimePilot-ramDeterministic-v3
TimePilot-ramNoFrameskip-v0
TimePilot-ramNoFrameskip-v3
TimePilot-v0
TimePilot-v3
TimePilotDeterministic-v0
TimePilotDeterministic-v3
TimePilotNoFrameskip-v0
TimePilotNoFrameskip-v3
Tutankham-ram-v0
Tutankham-ram-v3
Tutankham-ramDeterministic-v0
Tutankham-ramDeterministic-v3
Tutankham-ramNoFrameskip-v0
Tutankham-ramNoFrameskip-v3
Tutankham-v0
Tutankham-v3
TutankhamDeterministic-v0
TutankhamDeterministic-v3
TutankhamNoFrameskip-v0
TutankhamNoFrameskip-v3
TwoRoundDeterministicReward-v0
TwoRoundNondeterministicReward-v0
UpNDown-ram-v0
UpNDown-ram-v3
UpNDown-ramDeterministic-v0
UpNDown-ramDeterministic-v3
UpNDown-ramNoFrameskip-v0
UpNDown-ramNoFrameskip-v3
UpNDown-v0
UpNDown-v3
UpNDownDeterministic-v0
UpNDownDeterministic-v3
UpNDownNoFrameskip-v0
UpNDownNoFrameskip-v3
Venture-ram-v0
Venture-ram-v3
Venture-ramDeterministic-v0
Venture-ramDeterministic-v3
Venture-ramNoFrameskip-v0
Venture-ramNoFrameskip-v3
Venture-v0
Venture-v3
VentureDeterministic-v0
VentureDeterministic-v3
VentureNoFrameskip-v0
VentureNoFrameskip-v3
VideoPinball-ram-v0
VideoPinball-ram-v3
VideoPinball-ramDeterministic-v0
VideoPinball-ramDeterministic-v3
VideoPinball-ramNoFrameskip-v0
VideoPinball-ramNoFrameskip-v3
VideoPinball-v0
VideoPinball-v3
VideoPinballDeterministic-v0
VideoPinballDeterministic-v3
VideoPinballNoFrameskip-v0
VideoPinballNoFrameskip-v3
Walker2d-v1
WizardOfWor-ram-v0
WizardOfWor-ram-v3
WizardOfWor-ramDeterministic-v0
WizardOfWor-ramDeterministic-v3
WizardOfWor-ramNoFrameskip-v0
WizardOfWor-ramNoFrameskip-v3
WizardOfWor-v0
WizardOfWor-v3
WizardOfWorDeterministic-v0
WizardOfWorDeterministic-v3
WizardOfWorNoFrameskip-v0
WizardOfWorNoFrameskip-v3
YarsRevenge-ram-v0
YarsRevenge-ram-v3
YarsRevenge-ramDeterministic-v0
YarsRevenge-ramDeterministic-v3
YarsRevenge-ramNoFrameskip-v0
YarsRevenge-ramNoFrameskip-v3
YarsRevenge-v0
YarsRevenge-v3
YarsRevengeDeterministic-v0
YarsRevengeDeterministic-v3
YarsRevengeNoFrameskip-v0
YarsRevengeNoFrameskip-v3
Zaxxon-ram-v0
Zaxxon-ram-v3
Zaxxon-ramDeterministic-v0
Zaxxon-ramDeterministic-v3
Zaxxon-ramNoFrameskip-v0
Zaxxon-ramNoFrameskip-v3
Zaxxon-v0
Zaxxon-v3
ZaxxonDeterministic-v0
ZaxxonDeterministic-v3
ZaxxonNoFrameskip-v0
ZaxxonNoFrameskip-v3

About

Reinforcement learning agents trying to master the OpenAI universe

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages