proroklab/VectorizedMultiAgentSimulator
VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.
PythonGPL-3.0
Stargazers
- 0x00000499DaLian
- AcciorocketshipsUniversity of Cambridge
- AdrienLin1
- ak-ty
- alvaro-serraRLG, LIACS, Leiden University
- bipalium
- coolheroKorea Telecom
- GoingMyWay
- Harshavardhan341Mumbai
- JacopoPanUniversity of Toronto, @VectorInstitute
- janblumenkampUniversity of Cambridge
- Jarvis-KECNU
- Jerome-CongTsinghua University
- keep9oingUNIST
- lcpz
- Lee-JaeWonCILAB @ Yonsei Univ.
- ljaniecWrocław University of Science and Technology
- lstrichashl
- LT310
- LuckyLeeLL
- lyp741
- matteobettiniUniversity of Cambridge
- Pupillen@ZJU-FAST-Lab
- QingbiaoLiComputer Lab, The University of Cambridge
- rainorangelemonSan Diego
- ranzuhEspoo, Finland
- rawlaw001
- rdnfnUniversity of Cambridge
- RedaElmarSchool of Information Sciences [ ESI ]
- SamuraiChamplooZhejiang University
- samvelyan@google-deepmind
- sbhattacFayetteville State University
- sjYoondeltarSeoul
- srikrishna3118
- toberain
- xmzzyoPeking University