-
MineRL Diamond
The MineRL Diamond dataset is a large-scale dataset of Minecraft demonstrations, focusing on the development of sample-efficient reinforcement learning algorithms for mining... -
KGS 0.5-Komi Games
A dataset of KGS 0.5-komi games, used to train the value network. -
KGS 6.5-Komi Games
A dataset of KGS 6.5-komi games, used to train the value network. -
KGS 7.5-Komi Games
A dataset of KGS 7.5-komi games, used to train the value network. -
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. -
Tic-Tac-Toe Dataset
The dataset used in the paper is a collection of tic-tac-toe games, where each game is represented as a 9-qubit encoding. The games are encoded using Pauli-X rotations on... -
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. -
Catch Game Dataset
The dataset used for the game 'Catch' task, consisting of 28x28 binary pixel images. -
SAI Dataset
The dataset used for training the SAI agent, containing 7x7 Go games with multiple komi values. -
Tic-Tac-Toe
The dataset used in the paper is a collection of 6 publicly available datasets from the UCI Machine Learning repository. -
StarCraft II unit micromanagement benchmark
The dataset used in the paper is a multi-agent reinforcement learning dataset, where agents learn to coordinate their actions to achieve a common goal. -
Reconnaissance Blind TicTacToe
The Reconnaissance Blind TicTacToe (RBT) dataset is a variation of the Reconnaissance Blind Chess (RBC) challenge. It is a game of TicTacToe where the agent cannot see the moves... -
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. -
Atari Environment
The dataset used in this work is the Atari environment in OpenAI Gym, created by the Arcade Learning Environment (ALE).
