Man pages for markdumke/reinforcelearn
Reinforcement Learning

CliffWalking	Cliff Walking
Eligibility	Eligibility traces
Environment	Custom Reinforcement Learning Environment
EpsilonGreedyPolicy	Epsilon Greedy Policy
getEligibilityTraces	Get eligibility traces
getReplayMemory	Get replay memory.
getStateValues	Get state values.
getValueFunction	Get weights of value function.
gridworld	Gridworld
GymEnvironment	Gym Environment
interact	Interaction between agent and environment.
makeAgent	Create Agent.
makeAlgorithm	Make reinforcement learning algorithm.
makeEnvironment	Create reinforcement learning environment.
makePolicy	Create policy.
makeReplayMemory	Experience Replay
makeValueFunction	Value Function Representation
MdpEnvironment	MDP Environment
MountainCar	Mountain Car
nHot	Make n hot vector.
QLearning	Q-Learning
RandomPolicy	Random Policy
reinforcelearn	Reinforcement Learning.
SoftmaxPolicy	Softmax Policy
tilecoding	Tile Coding
ValueNetwork	Value Network
ValueTable	Value Table
windyGridworld	Windy Gridworld