Search Results for author: Marc Brittain

Found 8 papers, 0 papers with code

Integrated Conflict Management for UAM with Strategic Demand Capacity Balancing and Learning-based Tactical Deconfliction

no code implementations17 May 2023 Shulu Chen, Antony Evans, Marc Brittain, Peng Wei

By using DCB to precondition traffic to proper density levels, we show that reinforcement learning can achieve much better performance for tactical safety separation.

Management reinforcement-learning

Reward Function Optimization of a Deep Reinforcement Learning Collision Avoidance System

no code implementations1 Dec 2022 Cooper Cone, Michael Owen, Luis Alvarez, Marc Brittain

The proliferation of unmanned aircraft systems (UAS) has caused airspace regulation authorities to examine the interoperability of these aircraft with collision avoidance systems initially designed for large transport category aircraft.

Collision Avoidance reinforcement-learning +1

AAM-Gym: Artificial Intelligence Testbed for Advanced Air Mobility

no code implementations9 Jun 2022 Marc Brittain, Luis E. Alvarez, Kara Breeden, Ian Jessen

We introduce AAM-Gym, a research and development testbed for Advanced Air Mobility (AAM).

Safety Enhancement for Deep Reinforcement Learning in Autonomous Separation Assurance

no code implementations5 May 2021 Wei Guo, Marc Brittain, Peng Wei

We demonstrate the effectiveness of the two sub-modules in an open-source air traffic simulator with challenging environment settings.

Data Augmentation reinforcement-learning +1

A Deep Multi-Agent Reinforcement Learning Approach to Autonomous Separation Assurance

no code implementations17 Mar 2020 Marc Brittain, Xuxi Yang, Peng Wei

A novel deep multi-agent reinforcement learning framework is proposed to identify and resolve conflicts among a variable number of aircraft in a high-density, stochastic, and dynamic sector.

Multi-agent Reinforcement Learning reinforcement-learning +1

Prioritized Sequence Experience Replay

no code implementations25 May 2019 Marc Brittain, Josh Bertram, Xuxi Yang, Peng Wei

Experience replay is widely used in deep reinforcement learning algorithms and allows agents to remember and learn from experiences from the past.

Q-Learning reinforcement-learning +1

Autonomous Air Traffic Controller: A Deep Multi-Agent Reinforcement Learning Approach

no code implementations2 May 2019 Marc Brittain, Peng Wei

Air traffic control is a real-time safety-critical decision making process in highly dynamic and stochastic environments.

Decision Making Multi-agent Reinforcement Learning +2

Hierarchical Reinforcement Learning with Deep Nested Agents

no code implementations18 May 2018 Marc Brittain, Peng Wei

Deep hierarchical reinforcement learning has gained a lot of attention in recent years due to its ability to produce state-of-the-art results in challenging environments where non-hierarchical frameworks fail to learn useful policies.

Hierarchical Reinforcement Learning reinforcement-learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.