|
bitrl & cuberl Documentation
Simulation engine for reinforcement learning agents
|
Classes | |
| class | DoubleQLearning |
| The class DoubleQLearning. Simple tabular implemtation of double q-learning algorithm. More... | |
| struct | DoubleQLearningConfig |
| class | ExpectedSARSA |
| The ExpectedSARSA class. Simple implementation of the expected SARSA algorithm. More... | |
| struct | QLearningConfig |
| The QLearningConfig struct. More... | |
| class | QLearningSolver |
| The QLearning class. Table based implementation of the Q-learning algorithm using epsilon-greedy policy. The implementation also allows for exponential decay of the used epsilon. More... | |
| struct | SarsaConfig |
| The SarsaConfig struct. More... | |
| class | SarsaSolver |
| The Sarsa class. More... | |
| class | TDAlgoBase |
| The TDAlgoBase class. Base class for deriving TD algorithms. More... | |