# Learning to Play General Video-Games via an Object Embedding Network

## TL;DR

This paper introduces an object embedding network that allows deep reinforcement learning agents to learn directly from object information in video games, improving efficiency and aligning more closely with human perception.

## Contribution

The paper presents a novel object embedding network that compresses variable-length object features into a fixed-length vector for DRL, enabling learning directly from object data instead of raw pixels.

## Key findings

- Performance comparable to state-of-the-art methods
- Efficient learning from object information
- Improved alignment with human perception

## Abstract

Deep reinforcement learning (DRL) has proven to be an effective tool for creating general video-game AI. However most current DRL video-game agents learn end-to-end from the video-output of the game, which is superfluous for many applications and creates a number of additional problems. More importantly, directly working on pixel-based raw video data is substantially distinct from what a human player does.In this paper, we present a novel method which enables DRL agents to learn directly from object information. This is obtained via use of an object embedding network (OEN) that compresses a set of object feature vectors of different lengths into a single fixed-length unified feature vector representing the current game-state and fulfills the DRL simultaneously. We evaluate our OEN-based DRL agent by comparing to several state-of-the-art approaches on a selection of games from the GVG-AI Competition. Experimental results suggest that our object-based DRL agent yields performance comparable to that of those approaches used in our comparative study.