seldonian.RL.Agents.Discrete_Random_Agent.Discrete_Random_Agent

class Discrete_Random_Agent(env_description)

Bases: Agent

__init__(env_description)

An agent that acts on discrete observation and action spaces. Picks actions according to uniform random policy. Is not capable of learning.

Parameters:

env_description (Env_Description) – an object for accessing attributes of the environment

__repr__()

Return repr(self).

Methods

choose_action(observation)

Choose action from discrete uniform random distribution. Does not use observation to inform action.

Parameters:

observation – Environment-specific observation.

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 uniform random probability. Does not use observation or action.

Parameters:

• observation – The current observation of the agent.

• observation – The action taken by the agent from this observation.

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. Not used in this agent. To be overriden