2 datasets found

Groups: Reinforcement Learning

Filter Results

  • Grid World

    The dataset used in the paper is a reinforcement learning dataset, specifically a Markov Decision Process (MDP) with a finite set of states and actions.

  • Grid-world task

    The dataset used in this paper is the Grid-world task, which is a simple grid-based environment. The dataset is used to evaluate the performance of the Self-correcting...