MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning
Driving safely requires multiple capabilities from human and intelligent agents, such as the generalizability to unseen environments, the safety awareness of the surrounding traffic, and the decision-making in complex multi-agent settings. Despite the great success of Reinforcement Learning (RL), mo...
Saved in:
Main Authors | , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
26.09.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Driving safely requires multiple capabilities from human and intelligent
agents, such as the generalizability to unseen environments, the safety
awareness of the surrounding traffic, and the decision-making in complex
multi-agent settings. Despite the great success of Reinforcement Learning (RL),
most of the RL research works investigate each capability separately due to the
lack of integrated environments. In this work, we develop a new driving
simulation platform called MetaDrive to support the research of generalizable
reinforcement learning algorithms for machine autonomy. MetaDrive is highly
compositional, which can generate an infinite number of diverse driving
scenarios from both the procedural generation and the real data importing.
Based on MetaDrive, we construct a variety of RL tasks and baselines in both
single-agent and multi-agent settings, including benchmarking generalizability
across unseen scenes, safe exploration, and learning multi-agent traffic. The
generalization experiments conducted on both procedurally generated scenarios
and real-world scenarios show that increasing the diversity and the size of the
training set leads to the improvement of the RL agent's generalizability. We
further evaluate various safe reinforcement learning and multi-agent
reinforcement learning algorithms in MetaDrive environments and provide the
benchmarks. Source code, documentation, and demo video are available at \url{
https://metadriverse.github.io/metadrive}. |
---|---|
DOI: | 10.48550/arxiv.2109.12674 |