Timezone: »

 
Poster
Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world
Eugene Vinitsky · Nathan Lichtlé · Xiaomeng Yang · Brandon Amos · Jakob Foerster

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #1024
in Poster Session 5 »
We introduce \textit{Nocturne}, a new 2D driving simulator for investigating multi-agent coordination under partial observability. The focus of Nocturne is to enable research into inference and theory of mind in real-world multi-agent settings without the computational overhead of computer vision and feature extraction from images. Agents in this simulator only observe an obstructed view of the scene, mimicking human visual sensing constraints. Unlike existing benchmarks that are bottlenecked by rendering human-like observations directly using a camera input, Nocturne uses efficient intersection methods to compute a vectorized set of visible features in a C++ back-end, allowing the simulator to run at $2000+$ steps-per-second. Using open-source trajectory and map data, we construct a simulator to load and replay arbitrary trajectories and scenes from real-world driving data. Using this environment, we benchmark reinforcement-learning and imitation-learning agents and demonstrate that the agents are quite far from human-level coordination ability and deviate significantly from the expert trajectories.
Keywords: multi-agent reinforcement learning · benchmark · Self-Driving · Human-Modeling · Simulator
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Eugene Vinitsky (UC Berkeley)
Nathan Lichtlé (Electrical Engineering & Computer Science Department, University of California, Berkeley)
Xiaomeng Yang (Facebook)
Brandon Amos (Facebook AI Research)
Jakob Foerster (University of Oxford)

Jakob Foerster received a CIFAR AI chair in 2019 and is starting as an Assistant Professor at the University of Toronto and the Vector Institute in the academic year 20/21. During his PhD at the University of Oxford, he helped bring deep multi-agent reinforcement learning to the forefront of AI research and interned at Google Brain, OpenAI, and DeepMind. He has since been working as a research scientist at Facebook AI Research in California, where he will continue advancing the field up to his move to Toronto. He was the lead organizer of the first Emergent Communication (EmeCom) workshop at NeurIPS in 2017, which he has helped organize ever since.

More from the Same Authors