search

aogara-ds / hoodwinked-website

A text-based game where language models learn to lie and to detect lies.
https://hoodwinked.ai
11 stars 1 forks source link

split up main.py according to classic RL parts #2

Closed iejMac closed 2 years ago

iejMac commented 2 years ago

player.py or agent.py is fine, maybe agent.py since an agent can be a player or a bot and then you just implement different ways of controlling agents (random, human, GPT-3)

environment.py - this is your Game class

aogara-ds commented 2 years ago

Nice, done here: https://github.com/aogara-ds/hoodwinked/commit/36a3b1f026e4fabc24438786f1aefa058ed373d3