|
bitrl & cuberl Documentation
Simulation engine for reinforcement learning agents
|
class RandomTabularPolicy More...
#include <random_tabular_policy.h>
Public Types | |
| typedef uint_t | output_type |
| The type returned when calling this->operator() | |
Public Member Functions | |
| RandomTabularPolicy () | |
| Constructor. | |
| RandomTabularPolicy (uint_t seed) | |
| Constructor Initialize with a seed. | |
| template<typename MatType > | |
| output_type | operator() (const MatType &q_map, uint_t state_idx) const |
| operator(). Given a | |
| template<typename VecTp > | |
| output_type | operator() (const VecTp &vec) const |
| operator(). Given a vector always returns the position of the maximum occuring element. If the given vector is empty returns CubeAIConsts::invalid_size_type | |
| template<typename MatType > | |
| output_type | get_action (const MatType &q_map, uint_t state_idx) |
| get_action. Given a | |
| template<typename VecTp > | |
| output_type | get_action (const VecTp &q_map) |
| get_action. Given a vector always returns the position of the maximum occuring element. If the given vector is empty returns CubeAIConsts::invalid_size_type | |
| void | on_episode (uint_t) noexcept |
| any actions the policy should perform on the given episode index | |
| void | reset () noexcept |
| Reset the policy. | |
class RandomTabularPolicy
The type returned when calling this->operator()
| cuberl::rl::policies::RandomTabularPolicy::RandomTabularPolicy | ( | ) |
Constructor.
|
explicit |
Constructor Initialize with a seed.
| output_type cuberl::rl::policies::RandomTabularPolicy::get_action | ( | const MatType & | q_map, |
| uint_t | state_idx | ||
| ) |
get_action. Given a
| RandomTabularPolicy::output_type cuberl::rl::policies::RandomTabularPolicy::get_action | ( | const VecTp & | q_map | ) |
get_action. Given a vector always returns the position of the maximum occuring element. If the given vector is empty returns CubeAIConsts::invalid_size_type
|
inlinenoexcept |
any actions the policy should perform on the given episode index
| output_type cuberl::rl::policies::RandomTabularPolicy::operator() | ( | const MatType & | q_map, |
| uint_t | state_idx | ||
| ) | const |
operator(). Given a
| RandomTabularPolicy::output_type cuberl::rl::policies::RandomTabularPolicy::operator() | ( | const VecTp & | vec | ) | const |
operator(). Given a vector always returns the position of the maximum occuring element. If the given vector is empty returns CubeAIConsts::invalid_size_type
|
inlinenoexcept |
Reset the policy.