Search Results for "maze"

...It contains standardized environments, tasks and datasets (observations, actions, rewards, terminals) aimed at enabling reproducible research in offline RL. Researchers can load a dataset for a given task (e.g., maze navigation, manipulation) and apply their algorithm without the need to collect fresh transitions, which accelerates experimentation and comparison. The API is based on Gymnasium (via gym.make) and each environment also exposes a method get_dataset() that returns the offline data to learn from. The repository emphasizes open science, reproducibility, and benchmarking at scale, making it easier to compare algorithms on equal footing.

Procgen (short for Procedural Generation Benchmark) is a suite of 16 procedurally generated, game-like reinforcement learning environments designed to evaluate generalization and sample efficiency in RL agents. Unlike fixed, deterministic environments, Procgen generates new levels (layouts, obstacles, visual variation) each episode, making it impossible for an agent to simply memorize trajectories. The environments are designed to run very quickly (thousands of steps per second on a single...

The EV3 Robot solves a Maze. The robot is controlled by a color sensor to find the walls, which are black lines. And it is controlled by a compass sensor to navigate through the maze. With the compass sensor, the robot can turn exactliy by 90°. The start of the maze is marked by a blue paper strip and the exit is marked by a green paper strip.

Warwick Maze Courseware