cuberl::rl::algos::td::SarsaSolver< EnvType, PolicyType > Class Template Reference

The Sarsa class. More...

#include <sarsa.h>

Inheritance diagram for cuberl::rl::algos::td::SarsaSolver< EnvType, PolicyType >:

Collaboration diagram for cuberl::rl::algos::td::SarsaSolver< EnvType, PolicyType >:

Public Types
typedef TDAlgoBase< EnvType >::env_type	env_type
	env_t
typedef TDAlgoBase< EnvType >::action_type	action_type
	action_t
typedef TDAlgoBase< EnvType >::state_type	state_type
	state_t
typedef PolicyType	policy_type
	action_selector_t
Public Types inherited from cuberl::rl::algos::td::TDAlgoBase< EnvType >
typedef EnvType	env_type
	env_t
typedef env_type::action_type	action_type
	action_t
typedef env_type::state_type	state_type
	state_t
Public Types inherited from cuberl::rl::algos::RLSolverBase< EnvType >
typedef EnvType	env_type

Public Member Functions
	SarsaSolver (SarsaConfig config, const PolicyType &selector)
	ExpectedSarsaSolver.
virtual void	actions_before_training_begins (env_type &)
	actions_before_training_begins. Execute any actions the algorithm needs before starting the iterations
virtual void	actions_after_training_ends (env_type &)
	actions_after_training_ends. Actions to execute after the training iterations have finisehd
virtual void	actions_before_episode_begins (env_type &, uint_t)
	actions_before_training_episode
virtual void	actions_after_episode_ends (env_type &, uint_t, const EpisodeInfo &)
	actions_after_training_episode
virtual EpisodeInfo	on_training_episode (env_type &, uint_t episode_idx)
	on_episode Do one on_episode of the algorithm
void	save (const std::string &filename) const
	Build the policy after training.
cuberl::rl::policies::MaxTabularPolicy	build_policy () const
	Build the policy after training.
Public Member Functions inherited from cuberl::rl::algos::td::TDAlgoBase< EnvType >
virtual	~TDAlgoBase ()=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::td::TDAlgoBase< EnvType >
	TDAlgoBase ()=default
	DPAlgoBase.
Protected Member Functions inherited from cuberl::rl::algos::RLSolverBase< EnvType >
	RLSolverBase ()=default
	Constructor.

Detailed Description

template<envs::discrete_world_concept EnvType, typename PolicyType>
class cuberl::rl::algos::td::SarsaSolver< EnvType, PolicyType >

The Sarsa class.

Member Typedef Documentation

action_type

template<envs::discrete_world_concept EnvType, typename PolicyType >

typedef TDAlgoBase<EnvType>::action_type cuberl::rl::algos::td::SarsaSolver< EnvType, PolicyType >::action_type

action_t

env_type

template<envs::discrete_world_concept EnvType, typename PolicyType >

typedef TDAlgoBase<EnvType>::env_type cuberl::rl::algos::td::SarsaSolver< EnvType, PolicyType >::env_type

env_t

policy_type

template<envs::discrete_world_concept EnvType, typename PolicyType >

typedef PolicyType cuberl::rl::algos::td::SarsaSolver< EnvType, PolicyType >::policy_type

action_selector_t

state_type

template<envs::discrete_world_concept EnvType, typename PolicyType >

typedef TDAlgoBase<EnvType>::state_type cuberl::rl::algos::td::SarsaSolver< EnvType, PolicyType >::state_type

state_t

Constructor & Destructor Documentation

SarsaSolver()

template<envs::discrete_world_concept EnvTp, typename PolicyType >

cuberl::rl::algos::td::SarsaSolver< EnvTp, PolicyType >::SarsaSolver	(	SarsaConfig	config,
		const PolicyType &	selector
	)

ExpectedSarsaSolver.

Member Function Documentation

actions_after_episode_ends()

template<envs::discrete_world_concept EnvType, typename PolicyType >

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

inlinevirtual

actions_after_training_episode

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

actions_after_training_ends()

template<envs::discrete_world_concept EnvTp, typename PolicyType >

void cuberl::rl::algos::td::SarsaSolver< EnvTp, PolicyType >::actions_after_training_ends ( env_type &  )

virtual

actions_after_training_ends. Actions to execute after the training iterations have finisehd

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

actions_before_episode_begins()

template<envs::discrete_world_concept EnvType, typename PolicyType >

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

inlinevirtual

actions_before_training_episode

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

actions_before_training_begins()

template<envs::discrete_world_concept EnvTp, typename PolicyType >

void cuberl::rl::algos::td::SarsaSolver< EnvTp, PolicyType >::actions_before_training_begins ( env_type &  env )

virtual

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

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

build_policy()

template<envs::discrete_world_concept EnvTp, typename PolicyType >

cuberl::rl::policies::MaxTabularPolicy cuberl::rl::algos::td::SarsaSolver< EnvTp, PolicyType >::build_policy

(

)

const

Build the policy after training.

on_training_episode()

template<envs::discrete_world_concept EnvTp, typename PolicyType >

EpisodeInfo cuberl::rl::algos::td::SarsaSolver< EnvTp, PolicyType >::on_training_episode ( env_type &  env, uint_t  episode_idx  )

virtual

on_episode Do one on_episode of the algorithm

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

save()

template<envs::discrete_world_concept EnvTp, typename PolicyType >

void cuberl::rl::algos::td::SarsaSolver< EnvTp, PolicyType >::save

(

const std::string &

filename

)

const

Build the policy after training.

---

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

• libs/cuberl/include/cuberl/rl/algorithms/td/sarsa.h