async_learning.hpp File Reference

#include <mlpack/prereqs.hpp>
#include "worker/one_step_q_learning_worker.hpp"
#include "worker/one_step_sarsa_worker.hpp"
#include "worker/n_step_q_learning_worker.hpp"
#include "training_config.hpp"
#include "async_learning_impl.hpp"

Include dependency graph for async_learning.hpp:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
class	mlpack::rl::AsyncLearning< WorkerType, EnvironmentType, NetworkType, UpdaterType, PolicyType >
	Wrapper of various asynchronous learning algorithms, e.g. More...
class	mlpack::rl::OneStepQLearningWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType >
	Forward declaration of OneStepQLearningWorker. More...
class	mlpack::rl::OneStepSarsaWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType >
	Forward declaration of OneStepSarsaWorker. More...
class	mlpack::rl::NStepQLearningWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType >
	Forward declaration of NStepQLearningWorker. More...

Namespaces
	mlpack
	Linear algebra utility functions, generally performed on matrices or vectors.

Typedefs
template<typename EnvironmentType , typename NetworkType , typename UpdaterType , typename PolicyType >
using	mlpack::rl::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	mlpack::rl::OneStepSarsa = AsyncLearning< OneStepSarsaWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType >, EnvironmentType, NetworkType, UpdaterType, PolicyType >
	Convenient typedef for async one step Sarsa. More...
template<typename EnvironmentType , typename NetworkType , typename UpdaterType , typename PolicyType >
using	mlpack::rl::NStepQLearning = AsyncLearning< NStepQLearningWorker< EnvironmentType, NetworkType, UpdaterType, PolicyType >, EnvironmentType, NetworkType, UpdaterType, PolicyType >
	Convenient typedef for async n step q-learning. More...

Detailed Description

Author

Shangtong Zhang

This file is the definition of AsyncLearning class, which is wrapper for various asynchronous learning algorithms.

mlpack is free software; you may redistribute it and/or modify it under the terms of the 3-clause BSD license. You should have received a copy of the 3-clause BSD license along with mlpack. If not, see http://www.opensource.org/licenses/BSD-3-Clause for more information.

Typedef Documentation

NStepQLearning

template<typename EnvironmentType , typename NetworkType , typename UpdaterType , typename PolicyType >

using mlpack::rl::NStepQLearning = typedef 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.

OneStepQLearning

template<typename EnvironmentType , typename NetworkType , typename UpdaterType , typename PolicyType >

using mlpack::rl::OneStepQLearning = typedef 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.

OneStepSarsa

template<typename EnvironmentType , typename NetworkType , typename UpdaterType , typename PolicyType >

using mlpack::rl::OneStepSarsa = typedef 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.