# Deep Reinforcement Learning for General Video Game AI

arXiv: https://arxiv.org/abs/1806.02448 · HTML: https://mlsanity.com/paper/1806.02448/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2018.

## Built on by (most cited first, 25 of 25)

- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot](https://mlsanity.com/paper/2107.06857/) (2021)
- [Offline Meta-Reinforcement Learning with Online Self-Supervision](https://mlsanity.com/paper/2107.03974/) (2021)
- [Machine Learning in Aerodynamic Shape Optimization](https://mlsanity.com/paper/2202.07141/) (2022)
- [High-Accuracy Model-Based Reinforcement Learning, a Survey](https://mlsanity.com/paper/2107.08241/) (2021)
- [Inspector: Pixel-Based Automated Game Testing via Exploration, Detection, and Investigation](https://mlsanity.com/paper/2207.08379/) (2022)
- [A Survey on Natural Language Video Localization](https://mlsanity.com/paper/2104.00234/) (2021)
- [Physics-informed attention-based neural network for solving non-linear partial differential equations](https://mlsanity.com/paper/2105.07898/) (2021)
- [UniG3D: A Unified 3D Object Generation Dataset](https://mlsanity.com/paper/2306.10730/) (2023)
- [PuzzleJAX: A Benchmark for Reasoning and Learning](https://mlsanity.com/paper/2508.16821/) (2025)
- [Model-based Offline Policy Optimization with Adversarial Network](https://mlsanity.com/paper/2309.02157/) (2023)
- [Pedestrian Collision Avoidance for Autonomous Vehicles at Unsignalized Intersection Using Deep Q-Network](https://mlsanity.com/paper/2105.00153/) (2021)
- [Game Mechanic Alignment Theory and Discovery](https://mlsanity.com/paper/2102.10247/) (2021)
- [Deep Reinforcement Learning Using a Low-Dimensional Observation Filter for Visual Complex Video Game Playing](https://mlsanity.com/paper/2204.11370/) (2022)
- [Tree-Based Reconstructive Partitioning: A Novel Low-Data Level Generation Approach](https://mlsanity.com/paper/2309.13071/) (2023)
- [Self-correcting Reward Shaping via Language Models for Reinforcement Learning Agents in Games](https://mlsanity.com/paper/2506.23626/) (2025)
- [Best Agent Identification for General Game Playing](https://mlsanity.com/paper/2507.00451/) (2025)
- [Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning](https://mlsanity.com/paper/2607.22732/) (2026)
- [Planning from video game descriptions](https://mlsanity.com/paper/2109.00449/) (2021)
- [Reliable validation of Reinforcement Learning Benchmarks](https://mlsanity.com/paper/2203.01075/) (2022)
- [Machine Learning based Anomaly Detection for Smart Shirt: A Systematic Review](https://mlsanity.com/paper/2203.03300/) (2022)
- [All by Myself: Learning Individualized Competitive Behaviour with a Contrastive Reinforcement Learning optimization](https://mlsanity.com/paper/2310.00964/) (2023)
- [MoMA: Model-based Mirror Ascent for Offline Reinforcement Learning](https://mlsanity.com/paper/2401.11380/) (2024)
- [Learning to Select Goals in Automated Planning with Deep-Q Learning](https://mlsanity.com/paper/2406.14779/) (2024)
- [A Safe Exploration Strategy for Model-free Task Adaptation in Safety-constrained Grid Environments](https://mlsanity.com/paper/2408.00997/) (2024)

## Abstract (arXiv)

The General Video Game AI (GVGAI) competition and its associated software framework provides a way of benchmarking AI algorithms on a large number of games written in a domain-specific description language. While the competition has seen plenty of interest, it has so far focused on online planning, providing a forward model that allows the use of algorithms such as Monte Carlo Tree Search. In this paper, we describe how we interface GVGAI to the OpenAI Gym environment, a widely used way of connecting agents to reinforcement learning problems. Using this interface, we characterize how widely used implementations of several deep reinforcement learning algorithms fare on a number of GVGAI games. We further analyze the results to provide a first indication of the relative difficulty of these games relative to each other, and relative to those in the Arcade Learning Environment under similar conditions.