bellman_td_forms package¶

Submodules¶

bellman_td_forms.qlearning module¶

class bellman_td_forms.qlearning.QLearning(approximator: ValueFunction, gamma=0.01)[source]¶

Bases: object

delta(state: List[float], action: float, next_state: List[float], next_action: float, reward: float)[source]¶

bellman_td_forms.sarsa_average_reward module¶

class bellman_td_forms.sarsa_average_reward.SarsaAverageReward(approximator: ValueFunction, beta=0.01)[source]¶

Bases: object

delta(state: List[float], action: float, next_state: List[float], next_action: float, reward: float)[source]¶

bellman_td_forms.td_form module¶

class bellman_td_forms.td_form.TDForm(td_form_type: Type, approximator: ValueFunction, parameters: List[float])[source]¶

Bases: object

class Type(value)[source]¶

Bases: Enum

An enumeration.

Q_LEARNING = 'q_learning'¶

SARSA_AVERAGE_REWARD = 'sarsa_average_reward'¶

delta(state: List[float], action: float, next_state: List[float], next_action: float, reward: float)[source]¶

Module contents¶