# Action-Conditional Video Prediction using Deep Networks in Atari Games

arXiv: https://arxiv.org/abs/1507.08750 · HTML: https://mlsanity.com/paper/1507.08750/

## Key facts

- Cited by 172 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2015.

## Built on by (most cited first, 30 of 172)

- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability](https://mlsanity.com/paper/2405.17398/) (2024)
- [Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving](https://mlsanity.com/paper/2311.17918/) (2023)
- [Language Conditioned Imitation Learning over Unstructured Data](https://mlsanity.com/paper/2005.07648/) (2020)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding](https://mlsanity.com/paper/2406.09411/) (2024)
- [PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2103.09504/) (2021)
- [Ctrl-World: A Controllable Generative World Model for Robot Manipulation](https://mlsanity.com/paper/2510.10125/) (2025)
- [Video Language Planning](https://mlsanity.com/paper/2310.10625/) (2023)
- [iVideoGPT: Interactive VideoGPTs are Scalable World Models](https://mlsanity.com/paper/2405.15223/) (2024)
- [mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs](https://mlsanity.com/paper/2512.15692/) (2025)
- [Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation](https://mlsanity.com/paper/2410.13232/) (2024)
- [DriveGAN: Towards a Controllable High-Quality Neural Simulation](https://mlsanity.com/paper/2104.15060/) (2021)
- [Pathdreamer: A World Model for Indoor Navigation](https://mlsanity.com/paper/2105.08756/) (2021)
- [EgoTaskQA: Understanding Human Tasks in Egocentric Videos](https://mlsanity.com/paper/2210.03929/) (2022)
- [Reinforcement Learning with Action-Free Pre-Training from Videos](https://mlsanity.com/paper/2203.13880/) (2022)
- [FitVid: Overfitting in Pixel-Level Video Prediction](https://mlsanity.com/paper/2106.13195/) (2021)
- [DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation](https://mlsanity.com/paper/2308.07498/) (2023)
- [PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation](https://mlsanity.com/paper/2601.03782/) (2026)
- [World Models for Autonomous Driving: An Initial Survey](https://mlsanity.com/paper/2403.02622/) (2024)
- [Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction](https://mlsanity.com/paper/2103.04174/) (2021)
- [Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences](https://mlsanity.com/paper/2002.09089/) (2020)
- [BYOL-Explore: Exploration by Bootstrapped Prediction](https://mlsanity.com/paper/2206.08332/) (2022)
- [Playable Video Generation](https://mlsanity.com/paper/2101.12195/) (2021)
- [Long-Context State-Space Video World Models](https://mlsanity.com/paper/2505.20171/) (2025)
- [Predicting Video with VQVAE](https://mlsanity.com/paper/2103.01950/) (2021)
- [Embodied AI Agents: Modeling the World](https://mlsanity.com/paper/2506.22355/) (2025)
- [Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain](https://mlsanity.com/paper/2109.06668/) (2021)

## Abstract (arXiv)

Motivated by vision-based reinforcement learning (RL) problems, in particular Atari games from the recent benchmark Aracade Learning Environment (ALE), we consider spatio-temporal prediction problems where future (image-)frames are dependent on control variables or actions as well as previous frames. While not composed of natural scenes, frames in Atari games are high-dimensional in size, can involve tens of objects with one or more objects being controlled by the actions directly and many other objects being influenced indirectly, can involve entry and departure of objects, and can involve deep partial observability. We propose and evaluate two deep neural network architectures that consist of encoding, action-conditional transformation, and decoding layers based on convolutional neural networks and recurrent neural networks. Experimental results show that the proposed architectures are able to generate visually-realistic frames that are also useful for control over approximately 100-step action-conditional futures in some games. To the best of our knowledge, this paper is the first to make and evaluate long-term predictions on high-dimensional video conditioned by control inputs.