|
bitrl & cuberl Documentation
Simulation engine for reinforcement learning agents
|
The TDAlgoBase class. Base class for deriving TD algorithms. More...
#include <td_algo_base.h>


Public Types | |
| 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 | |
| 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 | |
Protected Member Functions | |
| TDAlgoBase ()=default | |
| DPAlgoBase. | |
Protected Member Functions inherited from cuberl::rl::algos::RLSolverBase< EnvType > | |
| RLSolverBase ()=default | |
| Constructor. | |
The TDAlgoBase class. Base class for deriving TD algorithms.
| typedef env_type::action_type cuberl::rl::algos::td::TDAlgoBase< EnvType >::action_type |
action_t
| typedef EnvType cuberl::rl::algos::td::TDAlgoBase< EnvType >::env_type |
env_t
| typedef env_type::state_type cuberl::rl::algos::td::TDAlgoBase< EnvType >::state_type |
state_t
|
virtualdefault |
Destructor.
|
protecteddefault |
DPAlgoBase.
| name |