OneStepQLearningWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType > Class Template Reference

Forward declaration of OneStepQLearningWorker. More...

Public Types
using	ActionType = typename EnvironmentType::Action
using	StateType = typename EnvironmentType::State
using	TransitionType = std::tuple< StateType, ActionType, double, StateType >

Public Member Functions
	OneStepQLearningWorker (const UpdaterType &updater, const EnvironmentType &environment, const TrainingConfig &config, bool deterministic)
	Construct one step Q-Learning worker with the given parameters and environment. More...
	OneStepQLearningWorker (const OneStepQLearningWorker &other)
	Copy another OneStepQLearningWorker. More...
	OneStepQLearningWorker (OneStepQLearningWorker &&other)
	Take ownership of another OneStepQLearningWorker. More...
	~OneStepQLearningWorker ()
	Clean memory. More...
void	Initialize (NetworkType &learningNetwork)
	Initialize the worker. More...
OneStepQLearningWorker &	operator= (const OneStepQLearningWorker &other)
	Copy another OneStepQLearningWorker. More...
OneStepQLearningWorker &	operator= (OneStepQLearningWorker &&other)
	Take ownership of another OneStepQLearningWorker. More...
bool	Step (NetworkType &learningNetwork, NetworkType &targetNetwork, size_t &totalSteps, PolicyType &policy, double &totalReward)
	The agent will execute one step. More...

Detailed Description

template

<

typename

EnvironmentType

,

typename

NetworkType

,

typename

UpdaterType

,

typename

PolicyType

>

class mlpack::rl::OneStepQLearningWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType >

Forward declaration of OneStepQLearningWorker.

One step Q-Learning worker.

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.
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 147 of file async_learning.hpp.

Member Typedef Documentation

ActionType

using ActionType = typename EnvironmentType::Action

Definition at line 40 of file one_step_q_learning_worker.hpp.

StateType

using StateType = typename EnvironmentType::State

Definition at line 39 of file one_step_q_learning_worker.hpp.

TransitionType

using TransitionType = std::tuple<StateType, ActionType, double, StateType>

Definition at line 41 of file one_step_q_learning_worker.hpp.

Constructor & Destructor Documentation

OneStepQLearningWorker() [1/3]

OneStepQLearningWorker ( const UpdaterType &  updater, const EnvironmentType &  environment, const TrainingConfig &  config, bool  deterministic  )

inline

Construct one step Q-Learning worker with the given parameters and environment.

Parameters

updater	The optimizer.
environment	The reinforcement learning task.
config	Hyper-parameters.
deterministic	Whether it should be deterministic.

Definition at line 52 of file one_step_q_learning_worker.hpp.

OneStepQLearningWorker() [2/3]

OneStepQLearningWorker ( const OneStepQLearningWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType > &  other )

inline

Copy another OneStepQLearningWorker.

Parameters

other

OneStepQLearningWorker to copy.

Definition at line 72 of file one_step_q_learning_worker.hpp.

OneStepQLearningWorker() [3/3]

OneStepQLearningWorker ( OneStepQLearningWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType > &&  other )

inline

Take ownership of another OneStepQLearningWorker.

Parameters

other

OneStepQLearningWorker to take ownership of.

Definition at line 102 of file one_step_q_learning_worker.hpp.

~OneStepQLearningWorker()

~OneStepQLearningWorker ( )

inline

Clean memory.

Definition at line 204 of file one_step_q_learning_worker.hpp.

Member Function Documentation

Initialize()

void Initialize ( NetworkType &  learningNetwork )

inline

Initialize the worker.

Parameters

learningNetwork

The shared network.

Definition at line 215 of file one_step_q_learning_worker.hpp.

operator=() [1/2]

OneStepQLearningWorker& operator= ( const OneStepQLearningWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType > &  other )

inline

Copy another OneStepQLearningWorker.

Parameters

other

OneStepQLearningWorker to copy.

Definition at line 132 of file one_step_q_learning_worker.hpp.

operator=() [2/2]

OneStepQLearningWorker& operator= ( OneStepQLearningWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType > &&  other )

inline

Take ownership of another OneStepQLearningWorker.

Parameters

other

OneStepQLearningWorker to take ownership of.

Definition at line 169 of file one_step_q_learning_worker.hpp.

Step()

bool Step ( NetworkType &  learningNetwork, NetworkType &  targetNetwork, size_t &  totalSteps, PolicyType &  policy, double &  totalReward  )

inline

The agent will execute one step.

Parameters

learningNetwork	The shared learning network.
targetNetwork	The shared target network.
totalSteps	The shared counter for total steps.
policy	The shared behavior policy.
totalReward	This will be the episode return if the episode ends after this step. Otherwise this is invalid.

Returns

Indicate whether current episode ends after this step.

Definition at line 244 of file one_step_q_learning_worker.hpp.

References TrainingConfig::Discount(), TrainingConfig::GradientLimit(), TrainingConfig::StepLimit(), TrainingConfig::StepSize(), TrainingConfig::TargetNetworkSyncInterval(), and TrainingConfig::UpdateInterval().

---

The documentation for this class was generated from the following files:

• /home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/reinforcement_learning/async_learning.hpp
• /home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/reinforcement_learning/worker/one_step_q_learning_worker.hpp