-
30 Million Self-Play Games
A dataset of 30 million self-play games, which with four GTX 980Ti GPUs takes about 3 weeks. -
Breakout and Robot Pushing
The dataset used in the paper is an adapted version of the Atari baseline Breakout, and a simulated Robot pushing domain. -
Atari RAM Games
The dataset is used to demonstrate the effectiveness of the Discovery of Deep Options (DDO) algorithm in accelerating reinforcement learning. -
No Press Diplomacy Dataset
A large-scale dataset of No Press Diplomacy games, containing more than 150,000 human games. -
Hanabi-Map-Elites
The dataset is used to evaluate agents for the Hanabi card game, a cooperative card game with imperfect information. -
Tic-Tac-Toe
The dataset used in the paper is a collection of 6 publicly available datasets from the UCI Machine Learning repository. -
MineRL-v0 dataset
The MineRL-v0 dataset contains human demonstration data for tasks in Minecraft. -
MineRL BASALT competition
The MineRL BASALT competition dataset contains human demonstration data for four tasks in Minecraft. -
Breakout, SeaQuest, Space Invaders, and Qbert Environments
The dataset used in this work is the Breakout, SeaQuest, Space Invaders, and Qbert environments. -
The Arcade Learning Environment: An Evaluation Platform for General Agents
The Arcade Learning Environment (ALE) is a lasting and indispensable element of the RL researcher’s toolbox. It is also the focus of our work. Since its inception, hundreds of... -
The Arcade Learning Environment
The Arcade Learning Environment -
Car Racing game dataset
The dataset used in this paper is the Car Racing game dataset, which consists of pixel frames of a car racing game. -
Atari 2600 games dataset
The dataset used in this paper is the Atari 2600 games dataset, which consists of 50 Atari 2600 games. -
Atari 2600 domain
The Atari 2600 domain dataset, used for training and testing reinforcement learning algorithms. -
Atari 2600 game dataset
The dataset used in the paper is the Atari 2600 game dataset, which consists of 4 consecutive 80x80 gray-scale game frames as the input to the network. -
Super Mario Bros
The dataset used in the Generative Adversarial Exploration for Reinforcement Learning paper. -
Atari 2600
The dataset used in the paper is the Atari 2600 dataset, which consists of 49 games. The dataset is used to test the Successor Uncertainties algorithm. -
Human-level control through deep reinforcement learning
The dataset contains data from human-level control through deep reinforcement learning.