MACAD-Gym is a training platform for Multi-Agent Connected Autonomous Driving (MACAD) built on top of the CARLA Autonomous Driving simulator. MACAD-Gym provides OpenAI Gym-compatible learning environments for various driving scenarios for training Deep RL algorithms in homogeneous/heterogenous, communicating/non-communicating and other multi-agent settings. New environments and scenarios can be easily added using a simple, JSON-like configuration. Quick Start Install MACAD-Gym using pip install macad-gym. If you have CARLA installed, you can get going using the following 3 lines of code. If not, follow the Getting started steps. import gym import macad_gym env = gym.make("HomoNcomIndePOIntrxMASS3CTWN3-v0") # Your agent code here Any RL library that supports the OpenAI-Gym API can be used to train agents in MACAD-Gym. The MACAD-Agents repository provides sample agents as a starter. See full README for more information. Summary of updates in v0.1.3 Updated python package version @praveen-palanisamy (#16) Added github action for pub to PyPI on creation of a release Fixed release-drafter config: yaml value should be str @praveen-palanisamy (#12) Added no-response bot @praveen-palanisamy (#11) Added release-drafter @praveen-palanisamy (#10) Added example for a basic agent script @praveen-palanisamy (#9) Added fixed_delta_seconds when running in synchronous mode to allow for proper physics sub-stepping in sync @praveen-palanisamy (#8) Fixed typo and dict access in Agent interface example Updated README Added NeurIPS paper info to README