cuberl::rl::algos::td::ExpectedSARSA< EnvTp, ActionSelector > Class Template Reference

The ExpectedSARSA class. Simple implementation of the expected SARSA algorithm. More...

#include <expected_sarsa.h>

Inheritance diagram for cuberl::rl::algos::td::ExpectedSARSA< EnvTp, ActionSelector >:

Collaboration diagram for cuberl::rl::algos::td::ExpectedSARSA< EnvTp, ActionSelector >:

Public Types
typedef TDAlgoBase< EnvTp >::env_type	env_type
	env_t
typedef TDAlgoBase< EnvTp >::action_type	action_type
	action_t
typedef TDAlgoBase< EnvTp >::state_type	state_type
	state_t
typedef ActionSelector	action_selector_type
	action_selector_t
Public Types inherited from cuberl::rl::algos::td::TDAlgoBase< EnvTp >
typedef EnvTp	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
	ExpectedSARSA (uint_t n_episodes, real_t tolerance, real_t gamma, real_t eta, uint_t plot_f, env_type &env, uint_t max_num_iterations_per_episode, const ActionSelector &selector)
	Constructor.
	ExpectedSARSA (TDAlgoConfig config, env_type &env, const ActionSelector &selector)
	Constructor.
virtual void	on_episode () override final
	on_episode. Performs the iterations for one training episode
Public Member Functions inherited from cuberl::rl::algos::td::TDAlgoBase< EnvTp >
virtual	~TDAlgoBase ()=default
	Destructor.
Public Member Functions inherited from cuberl::rl::algos::RLSolverBase< EnvType >
virtual	~RLSolverBase ()=default
	Destructor.
virtual void	actions_before_training_begins (env_type &)=0
	actions_before_training_begins. Execute any actions the algorithm needs before starting the iterations
virtual void	actions_after_training_ends (env_type &)=0
	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)=0
	on_episode Do one on_episode of the algorithm

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

Detailed Description

template<envs::discrete_world_concept EnvTp, typename ActionSelector>
class cuberl::rl::algos::td::ExpectedSARSA< EnvTp, ActionSelector >

The ExpectedSARSA class. Simple implementation of the expected SARSA algorithm.

Member Typedef Documentation

action_selector_type

template<envs::discrete_world_concept EnvTp, typename ActionSelector >

typedef ActionSelector cuberl::rl::algos::td::ExpectedSARSA< EnvTp, ActionSelector >::action_selector_type

action_selector_t

action_type

template<envs::discrete_world_concept EnvTp, typename ActionSelector >

typedef TDAlgoBase<EnvTp>::action_type cuberl::rl::algos::td::ExpectedSARSA< EnvTp, ActionSelector >::action_type

action_t

env_type

template<envs::discrete_world_concept EnvTp, typename ActionSelector >

typedef TDAlgoBase<EnvTp>::env_type cuberl::rl::algos::td::ExpectedSARSA< EnvTp, ActionSelector >::env_type

env_t

state_type

template<envs::discrete_world_concept EnvTp, typename ActionSelector >

typedef TDAlgoBase<EnvTp>::state_type cuberl::rl::algos::td::ExpectedSARSA< EnvTp, ActionSelector >::state_type

state_t

Constructor & Destructor Documentation

ExpectedSARSA() [1/2]

template<envs::discrete_world_concept EnvTp, typename ActionSelector >

cuberl::rl::algos::td::ExpectedSARSA< EnvTp, ActionSelector >::ExpectedSARSA	(	uint_t	n_episodes,
		real_t	tolerance,
		real_t	gamma,
		real_t	eta,
		uint_t	plot_f,
		env_type &	env,
		uint_t	max_num_iterations_per_episode,
		const ActionSelector &	selector
	)

Constructor.

ExpectedSARSA() [2/2]

template<envs::discrete_world_concept EnvTp, typename ActionSelector >

cuberl::rl::algos::td::ExpectedSARSA< EnvTp, ActionSelector >::ExpectedSARSA	(	TDAlgoConfig	config,
		env_type &	env,
		const ActionSelector &	selector
	)

Constructor.

Member Function Documentation

on_episode()

template<envs::discrete_world_concept EnvTp, typename ActionSelector >

void cuberl::rl::algos::td::ExpectedSARSA< EnvTp, ActionSelector >::on_episode ( )

finaloverridevirtual

on_episode. Performs the iterations for one training episode

---

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

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