cuberl::rl::algos::RLSolverBase< EnvType > Class Template Reference

RLAlgoBase. Base class for RL algorithms. More...

#include <rl_algorithm_base.h>

Inheritance diagram for cuberl::rl::algos::RLSolverBase< EnvType >:

Collaboration diagram for cuberl::rl::algos::RLSolverBase< EnvType >:

Public Types
typedef EnvType	env_type

Public Member Functions
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

Protected Member Functions
	RLSolverBase ()=default
	Constructor.

Detailed Description

template<typename EnvType>
class cuberl::rl::algos::RLSolverBase< EnvType >

RLAlgoBase. Base class for RL algorithms.

Member Typedef Documentation

env_type

template<typename EnvType >

typedef EnvType cuberl::rl::algos::RLSolverBase< EnvType >::env_type

Constructor & Destructor Documentation

~RLSolverBase()

template<typename EnvType >

virtual cuberl::rl::algos::RLSolverBase< EnvType >::~RLSolverBase ( )

virtualdefault

Destructor.

RLSolverBase()

template<typename EnvType >

cuberl::rl::algos::RLSolverBase< EnvType >::RLSolverBase ( )

protecteddefault

Constructor.

Member Function Documentation

actions_after_episode_ends()

template<typename EnvType >

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

inlinevirtual

actions_after_training_episode

Reimplemented in cuberl::rl::algos::td::SarsaSolver< EnvType, PolicyType >, cuberl::rl::algos::dp::IterativePolicyEvalutationSolver< EnvType, PolicyType >, cuberl::rl::algos::dp::PolicyImprovement< EnvType, PolicyType >, cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >, and cuberl::rl::algos::dp::ValueIteration< EnvType >.

actions_after_training_ends()

template<typename EnvType >

virtual void cuberl::rl::algos::RLSolverBase< EnvType >::actions_after_training_ends ( env_type &  )

pure virtual

actions_after_training_ends. Actions to execute after the training iterations have finisehd

Implemented in cuberl::rl::algos::td::SarsaSolver< EnvType, PolicyType >, cuberl::rl::algos::dp::PolicyImprovement< EnvType, PolicyType >, cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >, cuberl::rl::algos::dp::ValueIteration< EnvType >, cubeai::rl::algos::mc::MCTSSolver< EnvTp, NodeTp >, cuberl::rl::algos::dp::IterativePolicyEvalutationSolver< EnvType, PolicyType >, and cuberl::rl::algos::dp::IterativePolicyEvalutationSolver< env_type, policy_type >.

actions_before_episode_begins()

template<typename EnvType >

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

inlinevirtual

actions_before_training_episode

Reimplemented in cuberl::rl::algos::td::SarsaSolver< EnvType, PolicyType >, cuberl::rl::algos::dp::IterativePolicyEvalutationSolver< EnvType, PolicyType >, cuberl::rl::algos::dp::PolicyImprovement< EnvType, PolicyType >, cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >, and cuberl::rl::algos::dp::ValueIteration< EnvType >.

actions_before_training_begins()

template<typename EnvType >

virtual void cuberl::rl::algos::RLSolverBase< EnvType >::actions_before_training_begins ( env_type &  )

pure virtual

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

Implemented in cuberl::rl::algos::td::SarsaSolver< EnvType, PolicyType >, cuberl::rl::algos::dp::PolicyImprovement< EnvType, PolicyType >, cubeai::rl::algos::mc::MCTSSolver< EnvTp, NodeTp >, cuberl::rl::algos::dp::IterativePolicyEvalutationSolver< EnvType, PolicyType >, cuberl::rl::algos::dp::IterativePolicyEvalutationSolver< env_type, policy_type >, cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >, and cuberl::rl::algos::dp::ValueIteration< EnvType >.

on_training_episode()

template<typename EnvType >

virtual EpisodeInfo cuberl::rl::algos::RLSolverBase< EnvType >::on_training_episode ( env_type &  , uint_t    )

pure virtual

on_episode Do one on_episode of the algorithm

Implemented in cuberl::rl::algos::td::SarsaSolver< EnvType, PolicyType >, cuberl::rl::algos::dp::IterativePolicyEvalutationSolver< EnvType, PolicyType >, cuberl::rl::algos::dp::IterativePolicyEvalutationSolver< env_type, policy_type >, cuberl::rl::algos::dp::PolicyImprovement< EnvType, PolicyType >, cuberl::rl::algos::dp::PolicyImprovement< env_type, policy_type >, cuberl::rl::algos::dp::PolicyIterationSolver< EnvType, PolicyType >, and cuberl::rl::algos::dp::ValueIteration< EnvType >.

---

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

• libs/cuberl/include/cuberl/rl/algorithms/rl_algorithm_base.h