rl_action_simulate: Simulate an RL Agent's Action

In jdtrat/rlsims: Simulate Reinforcement Learning Agents in R

Simulate an RL Agent's Action

Description

This is a generic function used to simulate an RL agent's action given a specific decision-making policy.

Usage

rl_action_simulate(policy, values, ...)

Arguments

policy	What policy should a decision be made under? Currently supported are softmax, greedy, and epsilon-greedy.
values	A numeric vector containing the current value estimates of each action.
...	Additional arguments passed to or from specific methods, such as tau when policy = "softmax" and epsilon when policy = "epsilonGreedy".

Value

A number representing which action will be taken given the chosen policy.

jdtrat/rlsims documentation built on March 26, 2022, 6:17 p.m.