Robotic Warehouse

The Robotic Warehouse is an MARL environment often used to simulate warehouse automation scenarios. It serves as a testbed for studying cooperative, competitive, and mixed interaction among multiple agents, such as robots. The environment is designed to model tasks commonly found in real-world warehouses, such as navigation, item retrieval, obstacle avoidance, and task allocation.

Official link: https://github.com/semitable/robotic-warehouse.git.

Installation

Method 1: Install from PyPI:

pip install rware

Method 2: Install from GitHub repository:

git clone git@github.com:uoe-agents/robotic-warehouse.git
cd robotic-warehouse
pip install -e .

To learn more about installation, see the official tutorialofficial tutorial.

APIs

class xuance.environment.multi_agent_env.robotic_warehouse.RoboticWarehouseEnv(*args, **kwargs)

Bases: RawMultiAgentEnv

Note: To make this environment successfully, the gym verison is suggested to be 0.21.0.

close()

Close your environment here

render(render_mode)

Render the environment, and return the images

reset()

Reset your environment, and return initialized observations and other information.

state()

Get the global state of the environment in current step.

step(actions)

Execute the actions and get next observations, rewards, and other information.