-
Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Le...
The dataset used in the paper is a collection of expert demonstrations for various tasks, including robotic manipulation, maze navigation, and Atari games. -
Diagnosing Bottlenecks in Deep Q-Learning Algorithms
The dataset used in the paper is a collection of expert demonstrations for various tasks, including robotic manipulation, maze navigation, and Atari games.
