Simulator#

A Simulator created using whatif dataset.

Given the current states and action, it is able to return next states, which allow user to perform what if analysis and planning.

AutoTokenizer

Auto tokenizer process input Whatif dataset and provide data-level helper functions for Trainer and Simulator.

GPTBuilder

Provides high-level APIs to train and evaluate a GPT model based on the data loaded in AutoTokenizer.

Simulator

This is a Simulator class that can provide recommendation for an action, and the associated value, given the current context.

SimulatorWrapper

Make a2rl.Simulator accept tokenized actions only, to conform to the gym-style which requires discrete actions as integers.