cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType > Class Template Reference

The policy iteration class. More...

#include <policy_iteration.h>

Inheritance diagram for cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >:

Collaboration diagram for cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >:

Public Types
typedef DPSolverBase< EnvType >::env_type	env_type
	env_t
typedef PolicyType	policy_type
	policy_type
Public Types inherited from cuberl::rl::algos::dp::DPSolverBase< EnvType >
typedef RLSolverBase< EnvType >::env_type	env_type
	The environment type the solver is using.
Public Types inherited from cuberl::rl::algos::RLSolverBase< EnvType >
typedef EnvType	env_type

Public Member Functions
	PolicyIterationSolver (PolicyIterationConfig config, uint_t action_space_size, policy_type &policy)
	PolicyIteration.
virtual void	actions_before_training_begins (env_type &env) override
	actions_before_training_begins. Execute any actions the algorithm needs before starting the iterations
virtual void	actions_after_training_ends (env_type &) override
	actions_after_training_ends. Actions to execute after the training iterations have finisehd
virtual void	actions_before_episode_begins (env_type &, uint_t) override
	actions_before_training_episode
virtual void	actions_after_episode_ends (env_type &, uint_t, const EpisodeInfo &) override
	actions_after_training_episode
virtual EpisodeInfo	on_training_episode (env_type &env, uint_t episode_idx) override
	on_episode Do one on_episode of the algorithm
void	save (const std::string &filename) const
	save
Public Member Functions inherited from cuberl::rl::algos::dp::DPSolverBase< EnvType >
virtual	~DPSolverBase ()=default
	Destructor.
Public Member Functions inherited from cuberl::rl::algos::RLSolverBase< EnvType >
virtual	~RLSolverBase ()=default
	Destructor.

Additional Inherited Members
Protected Member Functions inherited from cuberl::rl::algos::dp::DPSolverBase< EnvType >
	DPSolverBase ()=default
	DPAlgoBase.
Protected Member Functions inherited from cuberl::rl::algos::RLSolverBase< EnvType >
	RLSolverBase ()=default
	Constructor.

Detailed Description

template<typename EnvType, typename PolicyType>
class cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >

The policy iteration class.

Member Typedef Documentation

env_type

template<typename EnvType , typename PolicyType >

typedef DPSolverBase<EnvType>::env_type cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >::env_type

env_t

policy_type

template<typename EnvType , typename PolicyType >

typedef PolicyType cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >::policy_type

policy_type

Constructor & Destructor Documentation

PolicyIterationSolver()

template<typename EnvType , typename PolicyType >

cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >::PolicyIterationSolver	(	PolicyIterationConfig	config,
		uint_t	action_space_size,
		policy_type &	policy
	)

PolicyIteration.

Member Function Documentation

actions_after_episode_ends()

template<typename EnvType , typename PolicyType >

virtual void cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >::actions_after_episode_ends ( env_type &  , uint_t  , const EpisodeInfo &    )

inlineoverridevirtual

actions_after_training_episode

Reimplemented from cuberl::rl::algos::RLSolverBase< EnvType >.

actions_after_training_ends()

template<typename EnvType , typename PolicyType >

void cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >::actions_after_training_ends ( env_type &  )

overridevirtual

actions_after_training_ends. Actions to execute after the training iterations have finisehd

Implements cuberl::rl::algos::RLSolverBase< EnvType >.

actions_before_episode_begins()

template<typename EnvType , typename PolicyType >

virtual void cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >::actions_before_episode_begins ( env_type &  , uint_t    )

inlineoverridevirtual

actions_before_training_episode

Reimplemented from cuberl::rl::algos::RLSolverBase< EnvType >.

actions_before_training_begins()

template<typename EnvType , typename PolicyType >

void cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >::actions_before_training_begins ( env_type &  env )

overridevirtual

actions_before_training_begins. Execute any actions the algorithm needs before starting the iterations

Implements cuberl::rl::algos::RLSolverBase< EnvType >.

on_training_episode()

template<typename EnvType , typename PolicyType >

EpisodeInfo cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >::on_training_episode ( env_type &  env, uint_t  episode_idx  )

overridevirtual

on_episode Do one on_episode of the algorithm

Implements cuberl::rl::algos::RLSolverBase< EnvType >.

save()

template<typename EnvType , typename PolicyType >

void cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >::save

(

const std::string &

filename

)

const

save

Parameters

filename

---

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

• libs/cuberl/include/cuberl/rl/algorithms/dp/policy_iteration.h