Decentralized Multi-Agent Reinforcement Learning for Autonomous Aircraft Traffic Management in AAM Corridor Networks
By
[Submitted on 22 Jun 2026]
Summary
This research paper addresses the challenge of managing high-density autonomous aircraft traffic in Advanced Air Mobility (AAM) corridors. The authors propose a decentralized approach using multi-agent reinforcement learning (MARL) to coordinate aircraft in corridor networks without centralized management. They trained policies in single-corridor settings and tested them on complex multi-corridor networks with merges and splits in a zero-shot manner. Results show learned behaviors transfer well across varying traffic densities, network geometries, and heterogeneous vehicle performance, requiring only locally coordinated entry, traversal, and exit behaviors while collectively producing desirable traffic flows.
Source
bskyDecentralized Multi-Agent Reinforcement Learning for Autonomous Aircraft Traffic Management in AAM Corridor Networksarxiv.orgKey quotes
· 3 pulledAs autonomous aircraft are introduced at scale and traffic density increases, centralized management becomes insufficient to coordinate the large numbers of crewed and uncrewed aircraft.
Experimental results demonstrate that learned behaviors transfer well to scenarios with varying traffic density, network geometry, and heterogeneous vehicle performance, without needing centralized coordination or model retraining.
We find that although our policies require only locally coordinated entry, traversal, and exit behaviors, they collectively produce desirable traffic flows through the corridor network.
You might also wanna read
AgentGym-RL: A Reinforcement Learning Framework for Training LLM Agents in Multi-Turn Decision Making
This paper introduces AgentGym-RL, a unified reinforcement learning framework for training LLM agents to perform multi-turn interactive deci
arxiv.org·4d agoAgentGym-RL: A Reinforcement Learning Framework for Training LLM Agents in Multi-Turn Decision Making
This paper introduces AgentGym-RL, a unified reinforcement learning framework for training LLM agents to perform multi-turn interactive deci
arxiv.org·4d ago
Skill-MAS: A Meta-Skill Approach to Improving Multi-Agent Systems Without Retraining
Skill-MAS proposes a novel approach to LLM-based automatic Multi-Agent Systems (MAS) generation that bridges the gap between inference-time
arxiv.org·4d agoSkill-MAS: A Meta-Skill Approach to Improving Multi-Agent Systems Without Retraining
Skill-MAS proposes a novel approach to LLM-based automatic Multi-Agent Systems (MAS) generation that bridges the gap between inference-time
arxiv.org·4d ago
Terminal-Bench-RL Project Advances Terminal Agent Training with Reinforcement Learning
The article discusses the Terminal-Bench-RL project, which extends the rLLM framework by UC Berkeley Sky Lab to train long-horizon terminal
github.com·11mo ago
Self-play reinforcement learning with minimal human data produces human-compatible autonomous driving policies
This paper presents a novel approach to training autonomous driving policies that combines self-play reinforcement learning with a small amo
arxiv.org·4d agoSelf-play reinforcement learning with minimal human data produces human-compatible autonomous driving policies
This paper presents a novel approach to training autonomous driving policies that combines self-play reinforcement learning with a small amo
arxiv.org·4d ago
The Evolution of AI: From Static Benchmarks to Inference-Time Search for Autonomous Agents
The article explores the shift from traditional AI benchmarking to inference-time search as the future of AI development. It discusses how c
adlrocha.substack.com·5mo ago
New Benchmark Reveals High Rates of Outcome-Driven Constraint Violations in Autonomous AI Agents
Researchers introduce a new benchmark for evaluating autonomous AI agents' safety, specifically focusing on outcome-driven constraint violat
arxiv.org·4mo agoComments
Sign in to join the conversation.
No comments yet. Be the first.