Peng Wei

Wei Guo, Marc Brittain, Peng Wei

The separation assurance task will be extremely challenging for air traffic controllers in a complex and high density airspace environment. Deep reinforcement learning (DRL) was used to develop an autonomous separation assurance framework in our previous work where the learned model advised speed maneuvers. In order to improve the safety of this model in unseen environments with uncertainties, in this work we propose a safety module for DRL in autonomous separation assurance applications. The proposed module directly addresses both model uncertainty and state uncertainty to improve safety. Our safety module consists of two sub-modules: (1) the state safety sub-module is based on the execution-time data augmentation method to introduce state disturbances in the model input state; (2) the model safety sub-module is a Monte-Carlo dropout extension that learns the posterior distribution of the DRL model policy. We demonstrate the effectiveness of the two sub-modules in an open-source air traffic simulator with challenging environment settings. Through extensive numerical experiments, our results show that the proposed sub-safety modules help the DRL agent significantly improve its safety performance in an autonomous separation assurance task.

Shulu Chen, Antony Evans, Marc Brittain et al.

Urban air mobility (UAM) has the potential to revolutionize our daily transportation, offering rapid and efficient deliveries of passengers and cargo between dedicated locations within and around the urban environment. Before the commercialization and adoption of this emerging transportation mode, however, aviation safety must be guaranteed, i.e., all the aircraft have to be safely separated by strategic and tactical deconfliction. Reinforcement learning has demonstrated effectiveness in the tactical deconfliction of en route commercial air traffic in simulation. However, its performance is found to be dependent on the traffic density. In this project, we propose a novel framework that combines demand capacity balancing (DCB) for strategic conflict management and reinforcement learning for tactical separation. By using DCB to precondition traffic to proper density levels, we show that reinforcement learning can achieve much better performance for tactical safety separation. Our results also indicate that this DCB preconditioning can allow target levels of safety to be met that are otherwise impossible. In addition, combining strategic DCB with reinforcement learning for tactical separation can meet these safety levels while achieving greater operational efficiency than alternative solutions.

Xuxi Yang, Werner Duvaud, Peng Wei

Decision-making agents with planning capabilities have achieved huge success in the challenging domain like Chess, Shogi, and Go. In an effort to generalize the planning ability to the more general tasks where the environment dynamics are not available to the agent, researchers proposed the MuZero algorithm that can learn the dynamical model through the interactions with the environment. In this paper, we provide a way and the necessary theoretical results to extend the MuZero algorithm to more generalized environments with continuous action space. Through numerical results on two relatively low-dimensional MuJoCo environments, we show the proposed algorithm outperforms the soft actor-critic (SAC) algorithm, a state-of-the-art model-free deep reinforcement learning algorithm.

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. Currently the sector capacity is constrained by human air traffic controller's cognitive limitation. We investigate the feasibility of a new concept (autonomous separation assurance) and a new approach to push the sector capacity above human cognitive limitation. We propose the concept of using distributed vehicle autonomy to ensure separation, instead of a centralized sector air traffic controller. Our proposed framework utilizes Proximal Policy Optimization (PPO) that we modify to incorporate an attention network. This allows the agents to have access to variable aircraft information in the sector in a scalable, efficient approach to achieve high traffic throughput under uncertainty. Agents are trained using a centralized learning, decentralized execution scheme where one neural network is learned and shared by all agents. The proposed framework is validated on three challenging case studies in the BlueSky air traffic control environment. Numerical results show the proposed framework significantly reduces offline training time, increases performance, and results in a more efficient policy.

Joshua R. Bertram, Peng Wei

We present a method for pursuit/evasion that is highly efficient and and scales to large teams of aircraft. The underlying algorithm is an efficient algorithm for solving Markov Decision Processes (MDPs) that supports fully continuous state spaces. We demonstrate the algorithm in a team pursuit/evasion setting in a 3D environment using a pseudo-6DOF model and study performance by varying sizes of team members. We show that as the number of aircraft in the simulation grows, computational performance remains efficient and is suitable for real-time systems. We also define probability-to-win and survivability metrics that describe the teams' performance over multiple trials, and show that the algorithm performs consistently. We provide numerical results showing control inputs for a typical 1v1 encounter and provide videos for 1v1, 2v2, 3v3, 4v4, and 10v10 contests to demonstrate the ability of the algorithm to adapt seamlessly to complex environments.

Marc Brittain, Josh Bertram, Xuxi Yang et al.

Experience replay is widely used in deep reinforcement learning algorithms and allows agents to remember and learn from experiences from the past. In an effort to learn more efficiently, researchers proposed prioritized experience replay (PER) which samples important transitions more frequently. In this paper, we propose Prioritized Sequence Experience Replay (PSER) a framework for prioritizing sequences of experience in an attempt to both learn more efficiently and to obtain better performance. We compare the performance of PER and PSER sampling techniques in a tabular Q-learning environment and in DQN on the Atari 2600 benchmark. We prove theoretically that PSER is guaranteed to converge faster than PER and empirically show PSER substantially improves upon PER.

Marc Brittain, Peng Wei

Air traffic control is a real-time safety-critical decision making process in highly dynamic and stochastic environments. In today's aviation practice, a human air traffic controller monitors and directs many aircraft flying through its designated airspace sector. With the fast growing air traffic complexity in traditional (commercial airliners) and low-altitude (drones and eVTOL aircraft) airspace, an autonomous air traffic control system is needed to accommodate high density air traffic and ensure safe separation between aircraft. We propose a deep multi-agent reinforcement learning framework that is able to identify and resolve conflicts between aircraft in a high-density, stochastic, and dynamic en-route sector with multiple intersections and merging points. The proposed framework utilizes an actor-critic model, A2C that incorporates the loss function from Proximal Policy Optimization (PPO) to help stabilize the learning process. In addition we use a centralized learning, decentralized execution scheme where one neural network is learned and shared by all agents in the environment. We show that our framework is both scalable and efficient for large number of incoming aircraft to achieve extremely high traffic throughput with safety guarantee. We evaluate our model via extensive simulations in the BlueSky environment. Results show that our framework is able to resolve 99.97% and 100% of all conflicts both at intersections and merging points, respectively, in extreme high-density air traffic scenarios.

Syed Arbab Mohd Shihab, Caleb Logemann, Deepak-George Thomas et al.

Revenue management can enable airline corporations to maximize the revenue generated from each scheduled flight departing in their transportation network by means of finding the optimal policies for differential pricing, seat inventory control and overbooking. As different demand segments in the market have different Willingness-To-Pay (WTP), airlines use differential pricing, booking restrictions, and service amenities to determine different fare classes or products targeted at each of these demand segments. Because seats are limited for each flight, airlines also need to allocate seats for each of these fare classes to prevent lower fare class passengers from displacing higher fare class ones and set overbooking limits in anticipation of cancellations and no-shows such that revenue is maximized. Previous work addresses these problems using optimization techniques or classical Reinforcement Learning methods. This paper focuses on the latter problem - the seat inventory control problem - casting it as a Markov Decision Process to be able to find the optimal policy. Multiple fare classes, concurrent continuous arrival of passengers of different fare classes, overbooking and random cancellations that are independent of class have been considered in the model. We have addressed this problem using Deep Q-Learning with the goal of maximizing the reward for each flight departure. The implementation of this technique allows us to employ large continuous state space but also presents the potential opportunity to test on real time airline data. To generate data and train the agent, a basic air-travel market simulator was developed. The performance of the agent in different simulated market scenarios was compared against theoretically optimal solutions and was found to be nearly close to the expected optimal revenue.

Josh Bertram, Peng Wei

We present a method for a certain class of Markov Decision Processes (MDPs) that can relate the optimal policy back to one or more reward sources in the environment. For a given initial state, without fully computing the value function, q-value function, or the optimal policy the algorithm can determine which rewards will and will not be collected, whether a given reward will be collected only once or continuously, and which local maximum within the value function the initial state will ultimately lead to. We demonstrate that the method can be used to map the state space to identify regions that are dominated by one reward source and can fully analyze the state space to explain all actions. We provide a mathematical framework to show how all of this is possible without first computing the optimal policy or value function.

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. However, as problem domains become more complex, deep hierarchical reinforcement learning can become inefficient, leading to longer convergence times and poor performance. We introduce the Deep Nested Agent framework, which is a variant of deep hierarchical reinforcement learning where information from the main agent is propagated to the low level $nested$ agent by incorporating this information into the nested agent's state. We demonstrate the effectiveness and performance of the Deep Nested Agent framework by applying it to three scenarios in Minecraft with comparisons to a deep non-hierarchical single agent framework, as well as, a deep hierarchical framework.

Joshua R. Bertram, Peng Wei

We propose an algorithm for deterministic continuous Markov Decision Processes with sparse rewards that computes the optimal policy exactly with no dependency on the size of the state space. The algorithm has time complexity of $O( |R|^3 \times |A|^2 )$ and memory complexity of $O( |R| \times |A| )$, where $|R|$ is the number of reward sources and $|A|$ is the number of actions. Furthermore, we describe a companion algorithm that can follow the optimal policy from any initial state without computing the entire value function, instead computing on-demand the value of states as they are needed. The algorithm to solve the MDP does not depend on the size of the state space for either time or memory complexity, and the ability to follow the optimal policy is linear in time and space with the path length of following the optimal policy from the initial state. We demonstrate the algorithm operation side by side with value iteration on tractable MDPs.

Joshua R. Bertram, Xuxi Yang, Peng Wei

Markov Decision Processes (MDPs) are a mathematical framework for modeling sequential decision making under uncertainty. The classical approaches for solving MDPs are well known and have been widely studied, some of which rely on approximation techniques to solve MDPs with large state space and/or action space. However, most of these classical solution approaches and their approximation techniques still take much computation time to converge and usually must be re-computed if the reward function is changed. This paper introduces a novel alternative approach for exactly and efficiently solving deterministic, continuous MDPs with sparse reward sources. When the environment is such that the "distance" between states can be determined in constant time, e.g. grid world, our algorithm offers $O( |R|^2 \times |A|^2 \times |S|)$, where $|R|$ is the number of reward sources, $|A|$ is the number of actions, and $|S|$ is the number of states. Memory complexity for the algorithm is $O( |S| + |R| \times |A|)$. This new approach opens new avenues for boosting computational performance for certain classes of MDPs and is of tremendous value for MDP applications such as robotics and unmanned systems. This paper describes the algorithm and presents numerical experiment results to demonstrate its powerful computational performance. We also provide rigorous mathematical description of the approach.