# The Atari Grand Challenge Dataset

arXiv: https://arxiv.org/abs/1705.10998 · HTML: https://mlsanity.com/paper/1705.10998/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2017.

## Built on by (most cited first, 14 of 14)

- [Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations](https://mlsanity.com/paper/1904.06387/) (2019)
- [Sora as a World Model? A Complete Survey on Text-to-Video Generation](https://mlsanity.com/paper/2403.05131/) (2024)
- [Inverse reinforcement learning for video games](https://mlsanity.com/paper/1810.10593/) (2018)
- [The Generalization Gap in Offline Reinforcement Learning](https://mlsanity.com/paper/2312.05742/) (2023)
- [Benchmarking End-to-End Behavioural Cloning on Video Games](https://mlsanity.com/paper/2004.00981/) (2020)
- [Reinforcement Learning Under Algorithmic Triage](https://mlsanity.com/paper/2109.11328/) (2021)
- [Inverse Reinforcement Learning by Estimating Expertise of Demonstrators](https://mlsanity.com/paper/2402.01886/) (2024)
- [Unsupervised Image Decomposition with Phase-Correlation Networks](https://mlsanity.com/paper/2110.03473/) (2021)
- [A novel policy for pre-trained Deep Reinforcement Learning for Speech Emotion Recognition](https://mlsanity.com/paper/2101.00738/) (2021)
- [A Continual Offline Reinforcement Learning Benchmark for Navigation Tasks](https://mlsanity.com/paper/2506.02883/) (2025)
- [Adaptive Agent Architecture for Real-time Human-Agent Teaming](https://mlsanity.com/paper/2103.04439/) (2021)
- [IGN : Implicit Generative Networks](https://mlsanity.com/paper/2206.05860/) (2022)
- [Prosody as a Teaching Signal for Agent Learning: Exploratory Studies and Algorithmic Implications](https://mlsanity.com/paper/2410.23554/) (2024)
- [Meta-learning how to Share Credit among Macro-Actions](https://mlsanity.com/paper/2506.13690/) (2025)

## Abstract (arXiv)

Recent progress in Reinforcement Learning (RL), fueled by its combination, with Deep Learning has enabled impressive results in learning to interact with complex virtual environments, yet real-world applications of RL are still scarce. A key limitation is data efficiency, with current state-of-the-art approaches requiring millions of training samples. A promising way to tackle this problem is to augment RL with learning from human demonstrations. However, human demonstration data is not yet readily available. This hinders progress in this direction. The present work addresses this problem as follows. We (i) collect and describe a large dataset of human Atari 2600 replays -- the largest and most diverse such data set publicly released to date, (ii) illustrate an example use of this dataset by analyzing the relation between demonstration quality and imitation learning performance, and (iii) outline possible research directions that are opened up by our work.