Learning to Play General Video-Games via an Object Embedding Network
arXiv:1803.05262
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.
arXiv commentTo appear in IEEE CIG2018
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- Towards Deep Symbolic Reinforcement Learning
- A Deep Hierarchical Approach to Lifelong Learning in Minecraft
- Investigating Human Priors for Playing Video Games
- Visual Interaction Networks
- State of the Art Control of Atari Games Using Shallow Reinforcement Learning
- Grounding Language for Transfer in Deep Reinforcement Learning