def get_fa_qlearning(self) -> td0_fa.TD0:
return td0_fa.TD0(
self.get_mdp_rep_for_rl_fa(),
TDAlgorithm.QLearning,
self.softmax,
self.epsilon,
self.epsilon_half_life,
self.learning_rate,
self.num_episodes,
self.max_steps,
self.fa_spec
)
def get_fa_expected_sarsa(self) -> td0_fa.TD0:
return td0_fa.TD0(
self.get_mdp_rep_for_rl_fa(),
TDAlgorithm.ExpectedSARSA,
self.softmax,
self.epsilon,
self.epsilon_half_life,
self.learning_rate,
self.num_episodes,
self.max_steps,
self.fa_spec
)
def get_fa_sarsa(self) -> td0_fa.TD0:
return td0_fa.TD0(
self.get_mdp_rep_for_rl_fa(),
self.exploring_start,
TDAlgorithm.SARSA,
self.softmax,
self.epsilon,
self.epsilon_half_life,
self.num_episodes,
self.max_steps,
self.fa_spec
)