-
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... -
Grid path planning with deep reinforcement learning: Preliminary results
Grid path planning with deep reinforcement learning: Preliminary results.
