What can we Learn Even From the Weakest? Learning Sketches for Programmatic Strategies

03/22/2022
by   Leandro C. Medeiros, et al.
0

In this paper we show that behavioral cloning can be used to learn effective sketches of programmatic strategies. We show that even the sketches learned by cloning the behavior of weak players can help the synthesis of programmatic strategies. This is because even weak players can provide helpful information, e.g., that a player must choose an action in their turn of the game. If behavioral cloning is not employed, the synthesizer needs to learn even the most basic information by playing the game, which can be computationally expensive. We demonstrate empirically the advantages of our sketch-learning approach with simulated annealing and UCT synthesizers. We evaluate our synthesizers in the games of Can't Stop and MicroRTS. The sketch-based synthesizers are able to learn stronger programmatic strategies than their original counterparts. Our synthesizers generate strategies of Can't Stop that defeat a traditional programmatic strategy for the game. They also synthesize strategies that defeat the best performing method from the latest MicroRTS competition.

READ FULL TEXT
research
07/10/2023

Choosing Well Your Opponents: How to Guide the Synthesis of Programmatic Strategies

This paper introduces Local Learner (2L), an algorithm for providing a s...
research
01/22/2020

StarAI: Reducing incompleteness in the game of Bridge using PLP

Bridge is a trick-taking card game requiring the ability to evaluate pro...
research
03/15/2012

Learning Game Representations from Data Using Rationality Constraints

While game theory is widely used to model strategic interactions, a natu...
research
06/26/2018

Banach-Mazur Parity Games and Almost-sure Winning Strategies

Two-player stochastic games are games with two 2 players and a randomise...
research
09/03/2020

A Predictive Strategy for the Iterated Prisoner's Dilemma

The iterated prisoner's dilemma is a game that produces many counter-int...
research
07/07/2018

How game complexity affects the playing behavior of synthetic agents

Agent based simulation of social organizations, via the investigation of...
research
03/21/2020

Reward-Mediated Individual and Altruistic Behavior

Recent research has taken particular interest in observing the dynamics ...

Please sign up or login with your details

Forgot password? Click here to reset