Classes
class	Acrobot
	Implementation of Acrobot game. More...

class	AggregatedPolicy

class	AsyncLearning
	Wrapper of various asynchronous learning algorithms, e.g. More...

class	CartPole
	Implementation of Cart Pole task. More...

class	ContinuousDoublePoleCart
	Implementation of Continuous Double Pole Cart Balancing task. More...

class	ContinuousMountainCar
	Implementation of Continuous Mountain Car task. More...

class	DoublePoleCart
	Implementation of Double Pole Cart Balancing task. More...

class	GreedyPolicy
	Implementation for epsilon greedy policy. More...

class	MountainCar
	Implementation of Mountain Car task. More...

class	NStepQLearningWorker
	Forward declaration of NStepQLearningWorker. More...

class	OneStepQLearningWorker
	Forward declaration of OneStepQLearningWorker. More...

class	OneStepSarsaWorker
	Forward declaration of OneStepSarsaWorker. More...

class	Pendulum
	Implementation of Pendulum task. More...

class	PrioritizedReplay
	Implementation of prioritized experience replay. More...

class	QLearning
	Implementation of various Q-Learning algorithms, such as DQN, double DQN. More...

class	RandomReplay
	Implementation of random experience replay. More...

class	RewardClipping
	Interface for clipping the reward to some value between the specified maximum and minimum value (Clipping here is implemented as $g_{\text{clipped}} = \max(g_{\text{min}}, \min(g_{\text{min}}, g)))$ .) More...

class	SumTree
	Implementation of SumTree. More...

class	TrainingConfig

Typedefs
template < typename EnvironmentType , typename NetworkType , typename UpdaterType , typename PolicyType >
using	NStepQLearning = AsyncLearning< NStepQLearningWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType >, EnvironmentType, NetworkType, UpdaterType, PolicyType >
	Convenient typedef for async n step q-learning. More...

template < typename EnvironmentType , typename NetworkType , typename UpdaterType , typename PolicyType >
using	OneStepQLearning = AsyncLearning< OneStepQLearningWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType >, EnvironmentType, NetworkType, UpdaterType, PolicyType >
	Convenient typedef for async one step q-learning. More...

template < typename EnvironmentType , typename NetworkType , typename UpdaterType , typename PolicyType >
using	OneStepSarsa = AsyncLearning< OneStepSarsaWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType >, EnvironmentType, NetworkType, UpdaterType, PolicyType >
	Convenient typedef for async one step Sarsa. More...

Typedef Documentation

◆ NStepQLearning

using NStepQLearning = AsyncLearning<NStepQLearningWorker<EnvironmentType, NetworkType, UpdaterType, PolicyType>, EnvironmentType, NetworkType, UpdaterType, PolicyType>

Convenient typedef for async n step q-learning.

Template Parameters

EnvironmentType	The type of the reinforcement learning task.
NetworkType	The type of the network model.
UpdaterType	The type of the optimizer.
PolicyType	The type of the behavior policy.

Definition at line 233 of file async_learning.hpp.

using OneStepQLearning = AsyncLearning<OneStepQLearningWorker<EnvironmentType, NetworkType, UpdaterType, PolicyType>, EnvironmentType, NetworkType, UpdaterType, PolicyType>

Convenient typedef for async one step q-learning.

Template Parameters

EnvironmentType	The type of the reinforcement learning task.
NetworkType	The type of the network model.
UpdaterType	The type of the optimizer.
PolicyType	The type of the behavior policy.

Definition at line 197 of file async_learning.hpp.

using OneStepSarsa = AsyncLearning<OneStepSarsaWorker<EnvironmentType, NetworkType, UpdaterType, PolicyType>, EnvironmentType, NetworkType, UpdaterType, PolicyType>

Convenient typedef for async one step Sarsa.

Template Parameters

EnvironmentType	The type of the reinforcement learning task.
NetworkType	The type of the network model.
UpdaterType	The type of the optimizer.
PolicyType	The type of the behavior policy.

Definition at line 215 of file async_learning.hpp.