Corpus ID: 234469778

Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic

@article{Chen2021DeepMR,
  title={Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic},
  author={Dong Chen and Zhaojian Li and Yongqiang Wang and Longsheng Jiang and Yue Wang},
  journal={ArXiv},
  year={2021},
  volume={abs/2105.05701}
}
  • Dong Chen, Zhaojian Li, +2 authors Yue Wang
  • Published 2021
  • Computer Science, Engineering
  • ArXiv
On-ramp merging is a challenging task for autonomous vehicles (AVs), especially in mixed traffic where AVs coexist with human-driven vehicles (HDVs). In this paper, we formulate the mixed-traffic highway on-ramp merging problem as a multi-agent reinforcement learning (MARL) problem, where the AVs (on both merge lane and through lane) collaboratively learn a policy to adapt to HDVs to maximize the traffic throughput. We develop an efficient and scalable MARL framework that can be used in dynamic… Expand

References

SHOWING 1-10 OF 52 REFERENCES
Leveraging the Capabilities of Connected and Autonomous Vehicles and Multi-Agent Reinforcement Learning to Mitigate Highway Bottleneck Congestion
TLDR
An RL-based multi-agent CAV control model to operate in mixed traffic, suggesting that even at CAV percent share of corridor traffic as low as 10%, CAVs can significantly mitigate bottlenecks in highway traffic. Expand
Anti-Jerk On-Ramp Merging Using Deep Reinforcement Learning
TLDR
Deep Reinforcement Learning is used here for decentralized decision-making and longitudinal control for high-speed on-ramp merging and the relationship between collision avoidance for safety and jerk minimization for passenger comfort in the multi-objective reward function is investigated by obtaining the Pareto front. Expand
Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control
TLDR
This paper presents a fully scalable and decentralized MARL algorithm for the state-of-the-art deep RL agent, advantage actor critic (A2C), within the context of ATSC, and presents two methods to stabilize the learning procedure, by improving the observability and reducing the learning difficulty of each local agent. Expand
Deep Multi Agent Reinforcement Learning for Autonomous Driving
TLDR
This work presents two novel, scalable and centralized MARL training techniques (MA-MeSN, MA-BoN), which achieve faster convergence and higher cumulative reward in complex domains like autonomous driving simulators, and compares their performance to existing state-of-the-art algorithms, DIAL and IMS. Expand
Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic
TLDR
This work presents a reinforcement learning approach to learn how to interact with drivers with different cooperation levels and shows that the agent successfully learns how to navigate a dense merging scenario with less deadlocks than with online planning methods. Expand
Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning
  • P. Palanisamy
  • Computer Science, Mathematics
  • 2020 International Joint Conference on Neural Networks (IJCNN)
  • 2020
TLDR
This paper proposes the use of Partially Observable Markov Games (POSG) for formulating the connected autonomous driving problems with realistic assumptions and provides a taxonomy of multi-agent learning environments based on the nature of tasks, nature of agents and thenature of the environment to help in categorizing various autonomousdriving problems that can be addressed under the proposed formulation. Expand
Distributed Multiagent Coordinated Learning for Autonomous Driving in Highways Based on Dynamic Coordination Graphs
  • Chao Yu, Xin Wang, +6 authors Guozhen Tan
  • Computer Science
  • IEEE Transactions on Intelligent Transportation Systems
  • 2020
TLDR
Using dynamic coordination graph to model the continuously changing topology during vehicles’ interactions and come up with two basic learning approaches to coordinate the driving maneuvers for a group of vehicles, which are workable in a more complex and realistic setting with any number of vehicles. Expand
Combining Reinforcement Learning with Model Predictive Control for On-Ramp Merging
TLDR
An algorithm is presented which blends the model-free RL agent with the MPC solution and shows that it provides better trade-offs between all metrics -- passenger comfort, efficiency, crash rate and robustness. Expand
Efficient Large-Scale Fleet Management via Multi-Agent Deep Reinforcement Learning
TLDR
This paper proposes a contextual multi-agent reinforcement learning framework including two concrete algorithms, namely contextual deep Q-learning and contextualmulti-agent actor-critic, to achieve explicit coordination among a large number of agents adaptive to different contexts. Expand
Parameter Sharing Reinforcement Learning Architecture for Multi Agent Driving
TLDR
A novel architecture to learn multiple driving behaviors in a traffic scenario that can learn multiple behaviors independently as well as simultaneously is proposed and takes advantage of the homogeneity of agents and learns in a parameter sharing paradigm. Expand
...
1
2
3
4
5
...