United States

Reinforcement learning (RL) is an effective method for solving problems that require autonomous agents to learn the best way to act in complex environments. RLlib is a powerful tool for applying reinforcement learning to problems where there are multiple agents or when agents must take on multiple roles. There exist many resources for learning about RLlib from a theoretical or academic perspective, but there is a lack of materials for learning how to use RLlib to solve your own practical problems. This tutorial helps to fill that gap. We show you how to apply reinforcement learning to your problem by taking you through a custom environment and demonstrating how to apply RLlib to that environment. We make the code available on GitHub.

NAML 2022

Tutorial: RLlib for Deep Hierarchical Multiagent Reinforcement Learning

swam intelligence

robotics

artificial intelligence

machine learning

reinforcement learning

Naval Information Warfare Center Pacific is partnering with AFCEA San Diego chapter to host the workshop.

The NAML workshop is an opportunity for researchers from Navy research and development centers and our partner organizations to exchange technical ideas and to come together as a team.

The goals of NAML are:

* To spread awareness of current machine learning research relevant to Naval applications

* To connect machine learning researchers with experts in military requirements

* To build and strengthen collaborations within the defense research community

**Watch this video to hear about the AFCEA purpose.**

<iframe width=1280 height=706 frameborder="0" scrolling="no" src="https://screencast-o-matic.com/player/creleVVcvRh?v=6&ff=1&title=0&controls=1" allowfullscreen="true"></iframe>

NAML 2021

technical paper

##### For full functionality of Underline, please SHUT OFF your VPN, or use a personal device.


Naval Information Warfare Center Pacific is partnering with AFCEA San Diego chapter to host the workshop.

The NAML workshop is an opportunity for researchers from Navy research and development centers and our partner organizations to exchange technical ideas and to come together as a team.

The goals of NAML are:

To spread awareness of current machine learning research relevant to Naval applications

To connect machine learning researchers with experts in military requirements

To build and strengthen collaborations within the defense research community


<figure class="video_container">
  <iframe src="https://s3.amazonaws.com/pf-user-files-01/u-59356/uploads/2022-03-22/hk13mxo/NAML_ReceptionWithtitle.mp4" width=826  height=526  frameborder="0" allowfullscreen="true"> </iframe>
</figure>

Naval Information Warfare Center Pacific is partnering with AFCEA San Diego chapter to host the workshop. The NAML workshop is an opportunity for researchers from Navy research and development centers and our partner organizations to exchange technical ideas and to come together as a team.

The goals of NAML are:

To spread awareness of current machine learning research relevant to Naval applications

To connect machine learning researchers with experts in military requirements

To build and strengthen collaborations within the defense research community



Recent advances with artificial intelligence (AI) in industry and academia provide an opportunity to develop intelligent system agents capable of reliably competing against human experts in course-of-action analysis. The team trained agents using deep reinforcement learning in a prototype wargaming framework in naval scenarios. Team members conducted experiments to evaluate the performance of AI threat agents trained using multiple algorithms and parameter configurations in each scenario and identified configurations providing superior results. Trained agents were placed in a desktop wargaming framework to allow play against human opponents, enabling the team to identify areas for improvement. This presentation provides an overview of the wargaming framework, results of experimentation, and next steps.

Improving Course-of-Action Analysis in Naval Wargames with Reinforcement Learning

Control systems for unmanned undersea vehicles (UUVs) are typically implemented using proportional integral derivative (PID) control systems. PID control systems for UUVs are resource-intensive to tune because they require several engineers, marine operators, and ship crew working together to adjust the controller. Furthermore, PID controllers rely on complex dynamic system models that contain assumptions to reduce the computational complexity of the models but can degrade the controller's performance if an environmental condition is encountered that conflicts with an assumption. In this study, a deep reinforcement learning (DRL) control system based on the Deep Deterministic Policy Gradient (DDPG) algorithm is investigated for a UUV control system. The DDPG algorithm is model-free, meaning that a complex dynamic system model is not needed to learn and provide optimal control performance. DRL-based control systems are tuned autonomously, which can greatly reduce the resources needed for tuning. The drawback to deep reinforcement learning is that it is computationally and resource-intensive. This study investigates how mixed floating-point precision with loss scaling can be used to reduce the time and computational resources needed to train the DDPG agent. Numerical case studies are presented.

Mixed Precision Reinforcement Learning for Control Simulation of Unmanned Undersea Vehicles

In this paper we study the multi-agent pursuit-evasion problem, and present an extension of the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) deep reinforcement learning algorithm. Previous pursuit-evasion advancements with MADDPG have focused on training capture strategies dependent on the restriction of evader movement with environmental features. We demonstrate a method to train pursuer agents to collaboratively surround and encircle an evader for reliable capture without a strategy rooted in environment entrapment (i.e. cornering). Our method utilizes a novel two-stage, variable-aggression, continuous reward function based on geometrical inscribed circles (incircles), along with a corresponding observation space, with agents operating in an entrapment-disadvantaged environment. Our results show reliable capture of an intelligent, superior evader by three trained pursuers in open space with our encircling strategy.

Robotic Swarm Pursuit-Evasion Capture Strategy using Deep Reinforcement Learning - An Update

In this work, we study a cognitive radio network in which the objective is to maximize the throughput of a secondary user (SU) subject to a constraint on the collision probability with the primary user (PU). For a Markov transmission model of the PU, it has been shown that Age of Information (AoI) plays an important role in this optimization. We have previously developed a throughput-optimal secondary user sensing/transmission policy by solving the linear program for the optimal distribution of the PU state and the AoI of sensed information. This approach requires that the PU idle/transmission dynamics are known, which is not typically the case in practice. Therefore, we implement this approach within a reinforcement learning algorithm by learning the model and then applying the optimization to the learned model. Reinforcement learning algorithms are typically only concerned with maximizing rewards, and therefore do not account for the constraint of avoiding collisions with the PU. To control this cost as well as the reward, we apply a model-based reinforcement learning approach for constrained Markov Decision Processes (CMDP) based on Upper Confidence Reinforcement Learning (UCRL-CMDP), which has proven regret guarantees for the reward and cost. We compare this approach with a model-based (Dyna-Q) and a model-free (Actor-Critic) RL algorithm with a Lagrangian reward function to incorporate the constraint. Simulation results demonstrate that the UCRL-CMDP performs favorably compared with the other two approaches in terms of throughput and computational efficiency.

Online Learning of the Secondary User Policy in a Cognitive Radio Network with Constraints on a Markov Primary User with Unknown Dynamics

Mitigation of range-restricted communication blocks in a distributed swarm is of interest to the Navy, due to the existence of data sharing limitations in all types of sensors and missions carried out in communications-denied environments. If a distributed swarm is affected by a communications block or delay, individual members should still be able to cooperatively identify, evaluate, and act as a team to preserve mission success based on a number of critical parameters guiding the scenario. In our approach, individual members of a heterogeneous swarm in a communication blocked environment construct their own perceived Common Operating Picture (COP). We modified a previously proposed task allocation algorithm to account for incomplete member COPs, and implemented a communications-limiting algorithm in simulation space that emulates a real-world communications block. This block impacts the decision making and asset prioritization of the task allocation algorithm, and our work contributes to a better understanding of task allocation and swarm regrouping in a limited communications environment. Results suggest that compensating for a swarm’s incomplete COP in a limited communications environment achieves a higher likelihood of mission success, and that a quasi-centralized approach for task dissemination ultimately performed more reliably than a fully decentralized approach.

Performative Analysis of Sensor Limitations in Communications Denied Autonomous Swarms

Tactical mission planning for air combat missions is a human-intensive procedure to determine how to coordinate a diverse set of assets. This coordination becomes increasingly difficult due to the physical constraints of the system and the multiple time scales. This paper borrows from safety-critical control to formulate a mathematical description of a class of tactical mission plans. This mathematical description results in a Hamilton-Jacobi-Isaacs (HJI) partial differential equation (PDE). However, due to the curse of dimensionality, numerical solutions to this high dimensional PDE are computationally intensive. To produce a numerical solution, the HJI equation is solved using deep learning. This formulation illustrates the effectiveness and utility of differential games for mission planning through the solution of two games. The first game, the Air3D game, is a collision avoidance scenario between two vehicles. The second is the active target defense (ATD) game. An infinite time solution has been recently found in the controls literature. This paper determines a finite time approximation that is compared with the infinite time solution. In particular, the region of space that the defender protects in a finite time horizon is numerically estimated.

Misson Planning Using Differential Games and Deep Learning

Fast reorientation of space-based sensors is needed to increase ISR capacity and to respond to high-value targeting requests. Rapid reorientation maneuvers are realized by constructing and solving a nonlinear optimization problem that models the physics of the rotational motion as part of the ground process of mission operations. The solution trajectories are then uplinked to the spacecraft for attitude guidance. Attitude guidance commands for a spacecraft are a time-series of incremental rotations that are given to the attitude control system at the closed-loop feedback rate which is typically greater than 10 Hz.

In practical space systems, it is generally not possible to uplink reorientation commands as a finely sampled time-series (at or greater than 10 Hz) since this would quickly exhaust the capacity of a spacecraft’s command buffer. Instead, the current paradigm is to issue a reorientation command as a single time-tagged target orientation. Then, an on-board trajectory generator is used to construct an appropriate rotation command time-series at the closed-loop feedback rate which are then fed to the attitude guidance system. Typically, these on-board trajectory generators do not have the processing power to perform trajectory optimization and instead generate a feasible, but sub-optimal, time-series command set at the appropriate rate.

A potential solution to this problem is to compute and then compress the optimized time-series commands using an autoencoder. An autoencoder is an unsupervised machine learning application of a neural network that conducts a non-linear mapping of the inputs to a lower dimensional space, called the latent space, using the encoder portion of the autoencoder. It then reconstructs the same input from the latent space using the decoder portion of the autoencoder. With such a method, the optimized command sequence can be generated and encoded on the ground, then only the latent space is transmitted to the spacecraft and decoded on-board the spacecraft resulting in the reconstructed optimized rotation sequence at the closed-loop feedback rate. Given the time-series nature of the optimized command sequence, one appropriate architecture for the autoencoder is a long short term memory (LSTM) neural network autoencoder.

In this talk, we demonstrate the methodology for constructing and training the LSTM autoencoder and show the reconstruction error for different degrees of compression represented by decreasing dimensionality of the latent space. We then compare the reconstructed command sequence and the uncompressed time-optimal solutions using a flight simulation software at the closed-loop feedback rate. The result is a new and computationally efficient approach for implementing non-legacy maneuvers on board a spacecraft. There are numerous applications beyond spacecraft where this capability can benefit the DoD such as small unmanned vehicle operations and operations in degraded electromagnetic environments.

A Method to Compress and Transmit Optimal Reorientation Commands to a Spacecraft Using Long Short-Term Memory Neural Network Autoencoders

Current approaches for handling machinery control system (MCS) faults on unmanned surface vessels (USVs) are based on guidance and thresholds selected by subject matter experts. While this can be a robust method, it requires significant human input and validation testing in expected operating conditions. To provide vessels with greater autonomy, data driven approaches for MCS faults are of interest. Data driven approaches based on AI/ML, besides saving both time and money, may provide a constructive means to learn from past experience, learn new insights, and optimally handle faults based on the current environment and conditions (e.g. vessel speed, payload, or sea state). One significant challenge with using AI/ML approaches for fault handling is the issue of class balance – in general, one may have limited realizations or samples of a given fault. In order to positively utilize data from previous successful test events, this work proposes the casting the problem of fault detection as an outlier detection problem. By building a healthy state model, detection of deviations from the nominal state provide a means to recognize new or novel operating conditions or the failure or degradation of a given subsystem. By quantifying and tracking the healthy state, long-term trends and typical behavior can be identified. These metrics could also be used to schedule inspections and maintenance based on the condition of the vessel as opposed to predetermined ones. With most outlier detection methods, typically a given threshold probability needs to be selected. Optimal selection of this threshold requires observations of such an outlier. Given that many of the sensors used to trigger hull, mechanical, and electrical (HM&E) faults are sensors with stochastic components (e.g. temperature, pressure, etc.), this work focuses on providing the probability of observing a given sensor reading or fault based on prior measurements. Quantile regression forests (QRF) provide a means to identify outliers, produces measurement statistics, and handle the randomness associated with HM&E sensors. Given time, other AI/ML approaches may be compared to QRF. As many vessels have separate MCS for each subsystem, data engineering is needed to aggregate, synchronize, and decimate data as a preprocessing step. With no further preprocessing, preliminary work has found QRF to be useful to identity component failure. Future efforts plan to scale the training test set to aid in generating long-term trend and statistics and establishing a healthy baseline.

Application of AI/ML to Improve Unmanned Surface Vessel Machinery Control System Fault Handling

Autonomous systems, including self-driving cars and unmanned underwater/surface/ground/air/space vehicles, have caught the imagination of the press, the public, and personnel of the U.S. Department of Defense (DoD). Moreover, these systems increasingly harness the power of Artificial Intelligence and Machine Learning (AI/ML), more specifically Deep Learning (DL), for their operation. The stunning performance of deep learning algorithms in comparison to extant methods, including pattern matching, computational linguistics, statistical inferencing, and legacy machine-learning, has taken the world by storm. However, adoption of such systems in safety-critical applications has been the subject of intense debate and scrutiny, because of the propensity of these algorithms for erroneous operation, such as misdirection with seemingly innocuous signage, and their vulnerability to data poisoning and data sparsity attacks, leading to incorrect operation which can be both embarrassing and damaging. This has naturally led the DoD community to ask, “How do we harness this technology being unleashed upon the world, and yet keep our nation and warfighters safe?” Before we answer this question, however, it is important to note that trust is integral to DoD systems, including autonomous systems, and ensuring reliable system operations is paramount. Therefore, we need strategies to equip the DoD to design, build, deploy, and sustain autonomous systems that are trustworthy, secure, reliable, and dependable. In this paper, we investigate issues leading to poor performance and lack of robustness of autonomous systems based on machine learning, and discuss the state of the art for their mitigation.

Assuring Autonomous Cyber Physical Data Driven Systems (AA-CPDDS)

Autonomous Systems consist of different systems working together so they can sense, plan, and act to a dynamic environment. There is much confusion on what autonomous systems are. This session will explain what autonomous systems are and how machine teaching and simulation can collaborate to create autonomous systems. Machine Teaching is critical to autonomous systems. It is based on reinforcement learning. The differences between machine teaching and machine learning will also be clarified.

Premium content

Tutorial: RLlib for Deep Hierarchical Multiagent Reinforcement Learning

Downloads

Next from NAML 2022

Improving Course-of-Action Analysis in Naval Wargames with Reinforcement Learning

Similar lecture

Data Management for Artificial Intelligence and Machine Learning Implementation Across the Department of the Navy

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES