seldonian.RL.Agents.mountain_car_rough_solution.Mountain_car_rough_solution¶
- class Mountain_car_rough_solution¶
Bases:
Agent- __init__()¶
Base class for all RL agents. Override all methods below in child class implementation
- __repr__()¶
Return repr(self).
Methods
- choose_action(observation)¶
Choose an action given an observation. To be overridden
- Parameters:
observation – The current observation of the agent, type depends on environment.
- get_params()¶
Retrieve the parameters of the agent’s policy
- get_policy()¶
Retrieve the agent’s policy object
- get_prob_this_action(observation, action)¶
Get probability of a given action provided environment is in a observation. To be overridden
- Parameters:
observation – The current observation of the agent, type depends on environment.
observation – The current action of the agent, type depends on environment.
- set_new_params(theta)¶
Update the parameters of the agent’s policy to theta.
- Parameters:
theta – policy parameters
- update(observation, next_observation, reward, terminated)¶
Updates agent’s parameters according to the learning rule To be overriden
- Parameters:
observation – The current observation of the agent, type depends on environment.
next_observation – The observation of the agent after an action is taken
reward – The reward for taking the action
terminated (bool) – Whether next_observation is a terminal observation