DeepAI
Log In Sign Up

Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants

02/24/2021
by   Dennis J. N. J. Soemers, et al.
0

In this paper, we use fully convolutional architectures in AlphaZero-like self-play training setups to facilitate transfer between variants of board games as well as distinct games. We explore how to transfer trained parameters of these architectures based on shared semantics of channels in the state and action representations of the Ludii general game system. We use Ludii's large library of games and game variants for extensive transfer learning evaluations, in zero-shot transfer experiments as well as experiments with additional fine-tuning time.

READ FULL TEXT

page 1

page 2

page 3

page 4

01/27/2020

Polygames: Improved Zero Learning

Since DeepMind's AlphaZero, Zero learning quickly became the state-of-th...
07/29/2018

Visual Analogies between Atari Games for Studying Transfer Learning in RL

In this work, we ask the following question: Can visual analogies, learn...
04/06/2020

Zero-Shot Learning of Text Adventure Games with Sentence-Level Semantics

Reinforcement learning algorithms such as Q-learning have shown great pr...
04/26/2020

Warm-Start AlphaZero Self-Play Search Enhancements

Recently, AlphaZero has achieved landmark results in deep reinforcement ...
01/17/2022

Spatial State-Action Features for General Games

In many board games and other abstract games, patterns have been used as...
11/06/2021

Action Recognition using Transfer Learning and Majority Voting for CSGO

Presently online video games have become a progressively favorite source...
01/07/2018

Sample-Efficient Reinforcement Learning through Transfer and Architectural Priors

Recent work in deep reinforcement learning has allowed algorithms to lea...