Implementations of reinforcement learning algorithms and environments.
makeEnvironment
Environment
GymEnvironment
MdpEnvironment
Gridworld
WindyGridworld
CliffWalking
MountainCar
MountainCarContinuous
makePolicy
EpsilonGreedyPolicy
GreedyPolicy
SoftmaxPolicy
RandomPolicy
makeValueFunction
ValueTable
ValueNetwork
makeAlgorithm
QLearning
makeReplayMemory
Eligibility
makeAgent
getValueFunction
getReplayMemory
getEligibilityTraces
interact