maze-2d

The 'Maze-2D' dataset/benchmark contains 2D maze environments used to evaluate exploration strategies in visual reinforcement learning, particularly under conditions of sparse rewards.

Papers using maze-2d (5)

Neuro-Inspired Inverse Learning for Planning and Control2026Task-Aware Exploration via a Predictive Bisimulation Metric2026Generative Actor Critic2025DIAR: Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation2024Active Reinforcement Learning Strategies for Offline Policy Improvement2024