bitrl & cuberl Documentation
Simulation engine for reinforcement learning agents
Loading...
Searching...
No Matches
cuberl::rl::with_double_q_table_max_action_mixin Struct Reference

#include <rl_mixins.h>

Inheritance diagram for cuberl::rl::with_double_q_table_max_action_mixin:

Static Public Member Functions

template<typename TableTp , typename StateTp >
static uint_t max_action (const TableTp &q1_table, const TableTp &q2_table, const StateTp &state, uint_t n_actions)
 Returns the max action by averaging the state values from the two tables.
 
template<typename TableTp , typename StateTp >
static uint_t max_action (const TableTp &q1_table, const StateTp &state, uint_t n_actions)
 Returns the max action by averaging the state values from the two tables.
 

Member Function Documentation

◆ max_action() [1/2]

template<typename TableTp , typename StateTp >
uint_t with_double_q_table_max_action_mixin::max_action ( const TableTp &  q1_table,
const StateTp &  state,
uint_t  n_actions 
)
static

Returns the max action by averaging the state values from the two tables.

◆ max_action() [2/2]

template<typename TableTp , typename StateTp >
uint_t with_double_q_table_max_action_mixin::max_action ( const TableTp &  q1_table,
const TableTp &  q2_table,
const StateTp &  state,
uint_t  n_actions 
)
static

Returns the max action by averaging the state values from the two tables.


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