Robust Reinforcement Learning for General Video Game Playing

11/11/2020
by   Chengpeng Hu, et al.
39

Reinforcement learning has successfully learned to play challenging board and video games. However, its generalization ability remains under-explored. The General Video Game AI Learning Competition aims at designing agents that are capable of learning to play different games levels that were unseen during training. This paper presents the games, entries and results of the 2020 General Video Game AI Learning Competition, held at the Sixteenth International Conference on Parallel Problem Solving from Nature and the 2020 IEEE Conference on Games. Three new games with sparse, periodic and dense rewards, respectively, were designed for this competition and the test levels were generated by adding minor perturbations to training levels or combining training levels. In this paper, we also design a reinforcement learning agent, called Arcane, for general video game playing. We assume that it is more likely to observe similar local information in different levels rather than global information. Therefore, instead of directly inputting a single, raw pixel-based screenshot of current game screen, Arcane takes the encoded, transformed global and local observations of the game screen as two simultaneous inputs, aiming at learning local information for playing new levels. Two versions of Arcane, using a stochastic or deterministic policy for decision-making during test, both show robust performance on the game set of the 2020 General Video Game AI Learning Competition.

READ FULL TEXT

page 1

page 3

page 5

research
02/28/2018

General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms

General Video Game Playing (GVGP) aims at designing an agent that is cap...
research
05/22/2020

Evaluating Generalisation in General Video Game Playing

The General Video Game Artificial Intelligence (GVGAI) competition has b...
research
09/20/2022

Deep Q-Network for AI Soccer

Reinforcement learning has shown an outstanding performance in the appli...
research
09/10/2018

ViZDoom Competitions: Playing Doom from Pixels

This paper presents the first two editions of Visual Doom AI Competition...
research
12/29/2019

Speeding up reinforcement learning by combining attention and agency features

When playing video-games we immediately detect which entity we control a...
research
12/04/2015

Reuse of Neural Modules for General Video Game Playing

A general approach to knowledge transfer is introduced in which an agent...
research
04/02/2020

Benchmarking End-to-End Behavioural Cloning on Video Games

Behavioural cloning, where a computer is taught to perform a task based ...

Please sign up or login with your details

Forgot password? Click here to reset