Can Meta-Interpretive Learning outperform Deep Reinforcement Learning of Evaluable Game strategies?

02/26/2019
by   Céline Hocquette, et al.
0

World-class human players have been outperformed in a number of complex two person games (Go, Chess, Checkers) by Deep Reinforcement Learning systems. However, owing to tractability considerations minimax regret of a learning system cannot be evaluated in such games. In this paper we consider simple games (Noughts-and-Crosses and Hexapawn) in which minimax regret can be efficiently evaluated. We use these games to compare Cumulative Minimax Regret for variants of both standard and deep reinforcement learning against two variants of a new Meta-Interpretive Learning system called MIGO. In our experiments all tested variants of both normal and deep reinforcement learning have worse performance (higher cumulative minimax regret) than both variants of MIGO on Noughts-and-Crosses and Hexapawn. Additionally, MIGO's learned rules are relatively easy to comprehend, and are demonstrated to achieve significant transfer learning in both directions between Noughts-and-Crosses and Hexapawn.

READ FULL TEXT
research
09/17/2018

Object-sensitive Deep Reinforcement Learning

Deep reinforcement learning has become popular over recent years, showin...
research
12/24/2020

SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II

AlphaStar, the AI that reaches GrandMaster level in StarCraft II, is a r...
research
10/31/2017

Regret Minimization for Partially Observable Deep Reinforcement Learning

Deep reinforcement learning algorithms that estimate state and state-act...
research
03/27/2013

Predicting The Performance of Minimax and Product in Game-Tree

The discovery that the minimax decision rule performs poorly in some gam...
research
08/06/2017

An Information-Theoretic Optimality Principle for Deep Reinforcement Learning

In this paper, we methodologically address the problem of cumulative rew...
research
06/30/2015

Language Understanding for Text-based Games Using Deep Reinforcement Learning

In this paper, we consider the task of learning control policies for tex...
research
11/04/2022

Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI

In fighting games, individual players of the same skill level often exhi...

Please sign up or login with your details

Forgot password? Click here to reset