Results for “predictive deep reinforcement learning” — Page 3

NASA NTRS2017

Multi-Objective Reinforcement Learning-Based Deep Neural Networks for Cognitive Space Communications

Future communication subsystems of space exploration missions can potentially benefit from software-defined radios (SDRs) controlled by machine learning algorithms. In this paper, we propose a novel hybrid radio resource allocation management control algorithm that integrates multi-objective reinforcement learning and deep artificial neural networks. The objective is to efficiently manage communications system resources by monitoring performance functions with common dependent variables that result in conflicting goals. The uncertainty in the performance of thousands of different possible combinations of radio parameters makes the trade-off between exploration and exploitation in reinforcement learning (RL) much more challenging for future critical space-based missions. Thus, the system should spend as little time as possible on exploring actions, and whenever it explores an action, it should perform at acceptable levels most of the time. The proposed approach enables on-line learning by interactions with the environment and restricts poor resource allocation performance through virtual environment exploration. Improvements in the multiobjective performance can be achieved via transmitter parameter adaptation on a packet-basis, with poorly predicted performance promptly resulting in rejected decisions. Simulations presented in this work considered the DVB-S2 standard adaptive transmitter parameters and additional ones expected to be present in future adaptive radio systems. Performance results are provided by analysis of the proposed hybrid algorithm when operating across a satellite communication channel from Earth to GEO orbit during clear sky conditions. The proposed approach constitutes part of the core cognitive engine proof-of-concept to be delivered to the NASA Glenn Research Center SCaN Testbed located onboard the International Space Station.

space archtiecture↗

NASA NTRS2017

Multi-Objective Reinforcement Learning-based Deep Neural Networks for Cognitive Space Communications

Future communication subsystems of space exploration missions can potentially benefit from software-defined radios (SDRs) controlled by machine learning algorithms. In this paper, we propose a novel hybrid radio resource allocation management control algorithm that integrates multi-objective reinforcement learning and deep artificial neural networks. The objective is to efficiently manage communications system resources by monitoring performance functions with common dependent variables that result in conflicting goals. The uncertainty in the performance of thousands of different possible combinations of radio parameters makes the trade-off between exploration and exploitation in reinforcement learning (RL) much more challenging for future critical space-based missions. Thus, the system should spend as little time as possible on exploring actions, and whenever it explores an action, it should perform at acceptable levels most of the time. The proposed approach enables on-line learning by interactions with the environment and restricts poor resource allocation performance through virtual environment exploration. Improvements in the multiobjective performance can be achieved via transmitter parameter adaptation on a packet-basis, with poorly predicted performance promptly resulting in rejected decisions. Simulations presented in this work considered the DVB-S2 standard adaptive transmitter parameters and additional ones expected to be present in future adaptive radio systems. Performance results are provided by analysis of the proposed hybrid algorithm when operating across a satellite communication channel from Earth to GEO orbit during clear sky conditions. The proposed approach constitutes part of the core cognitive engine proof-of-concept to be delivered to the NASA Glenn Research Center SCaN Testbed located onboard the International Space Station.

space archtiecture↗

DOE OSTI2024

Learning Constrained Parametric Differentiable Predictive Control Policies With Guarantees

We present differentiable predictive control (DPC), a method for offline learning of constrained neural control policies for nonlinear dynamical systems with performance guarantees. We show that the sensitivities of the parametric optimal control problem can be used to obtain direct policy gradients. Specifically, we employ automatic differentiation (AD) to efficiently compute the sensitivities of the model predictive control (MPC) objective function and constraints penalties. To guarantee safety upon deployment, we derive probabilistic guarantees on closed-loop stability and constraint satisfaction based on indicator functions and Hoeffding’s inequality. We empirically demonstrate that the proposed method can learn neural control policies for various parametric optimal control tasks. In particular, we show that the proposed DPC method can stabilize systems with unstable dynamics, track time-varying references, and satisfy nonlinear state and input constraints. Our DPC method has practical time savings compared to alternative approaches for fast and memory-efficient controller design. Specifically, DPC does not depend on a supervisory controller as opposed to approximate MPC based on imitation learning. We demonstrate that, without losing performance, DPC is scalable with greatly reduced demands on memory and computation compared to implicit and explicit MPC while being more sample efficient than model-free reinforcement learning (RL) algorithms.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Reinforcement Learning Approach to Cybersecurity in Space (RELACSS)

Securing satellite groundstations against cyber-attacks is vital to national security missions. However, these cyber threats are constantly evolving. As vulnerabilities are discovered and patched, new vulnerabilities are discovered and exploited. In order to automate the process of discovering existing vulnerabilities and the means to exploit them, a reinforcement learning framework is presented in this report. We demonstrate that this framework can learn to successfully navigate an unknown network and detect nodes of interest despite the presence of a moving target defense. The agent then exfiltrates a file of interest from the node as quickly as possible. This framework also incorporates a defensive software agent that learns to impede the attacking agents progress. This setup allows for the agents to work against each other and improve their abilities. We anticipate that this capability will help uncover unforeseen vulnerabilities and the means to mitigate them. The modular nature of the framework enables users to swap out learning algorithms and modify the reward functions in order to adapt the learning tasks to various use cases and environments. Several algorithms, viz., tabular Q learning, deep Q networks, proximal policy optimization, advantage actor-critic, generative adversarial imitation learning, are explored for the agents and the results highlighted. The agent learns to solve the tasks in a light-weight abstract environment. Once the agent learns to perform sufficiently well, it can be deployed in a minimega virtual machine environment (or a real network) with wrappers that map abstract actions to software commands. The agent also uses a local representation of the actions called a ‘slot-mechanism’. This allows the agent to learn in a certain network and generalize it to different networks. The defensive agent learns to predict the actions taken by an offensive agent and uses that information to anticipate the threat. This information can then either be used to raise an alarm or to take actions to thwart the attack. We believe that with the appropriate reward design, a representative environment, and action set, this framework can be generalized to tackle other cybersecurity tasks. By sufficiently training these agents, we can anticipate vulnerabilities leading to robust future designs. We can also deploy automated defensive agents that can help secure satellite groundstation and their vital national security missions.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

DOE OSTI2021

The phylogenetic roots of addiction: compulsive drug seeking, natural and drug-sensitive reward, and the acquisition of learned habits

Our rational faculties permit us humans to maximize the utility of our actions. We perform a fundamental type of cost-benefit analysis in which we frame a problem, assign values to the different paths, and then choose from among a set of available options, the course that promises the most favorable outcome. So why then does addiction appear to be so impervious to the associated costs, so unaffected by undesired consequences, and ultimately so resistant to cognitive oversight? The answer may likely be found in the fact that the drivers for compulsive drug seeking and drug taking are located in affective brain circuits, circuits that are structured and patterned by learning with repeated activation. These deep processes exhibit significant resistance to control by our cognitive faculties. The general consensus is that addiction arises from mechanisms that overvalue the magnitude of reward, discount the associated risks, and thereby bias individuals towards compulsive pursuit of addictive drugs. Behavioral disruption and dependence appear to arise at the intersection of a number of connected but separate phenomena: expectations for the occurrence of specific events, behaviors that seek encounters with them, the ability to notice and learn nonrandom, co-occurring conditions, the prediction and valuation of consequences, the forming of enduring memories, and the drivers of focused behavior through compulsion, habits, and acquired routines. It is important to recognize that each one of these individual faculties are present and well developed across the entire phylogenetic tree of bilateral metazoans. The goal of this special volume is dedicated to exploring the degree to which inherent elements can account for addiction and addiction-associated phenomena. In much of the literature on addiction, the underlying processes are often viewed as distinctly mammalian, arising, in part, from the strong cognitive capacities of this taxon. Some phenomena may even be regarded to exist only in primates, or even solely in humans. This supposition arises from the fact that studies are conducted almost exclusively in mammals and primates, while evolutionary antecedents of the behavior are rarely considered. A more comprehensive perspective that examines drug reward and reinforcement in a wider range of organisms demonstrates that many of the component traits are actually well developed across the greater metazoan lineage, and they may well predate the emergence of a mammalian clade by a wide margin. The collection of papers assembled here supports the notion that the capacity to associate cues and quences has not arisen in mammals de novo. Rather, the neural mechanisms for detecting contingencies and for predicting future outcomes are very deeply rooted across broad phylogenetic divisions. Our understanding of an ability to associate paired events has been enriched by work in invertebrate preparations in both classical and operant conditioning scenarios [Cook and Carew, 1986, 1989a, 1989b]. The ability to learn allows us to connect cues and behavioral actions to their associated consequences. Pavlovian conditioning enriches surrounding cues with predictive value. Outcomes with positive valence generate appetitive responses and approach to the associated cues, while those perceived as aversive bring cue avoidance and withdrawal. Humans are not the only life forms capable of such short- and long-term modulations of behavior

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2020

DEEP Solar: Data DrivEn Modeling and Analytics for Enhanced System Layer ImPlementation

Realizing the SETO 2030 mission of reducing solar energy costs to 3-5 c/kWh will require innovative enabling research on effective, cost-efficient integration of local PV within distribution systems. However, the intermittent and variable nature of PVs compels operators to impose conservative hosting capacity constraints. Given the extremely high variability of (intermittent and unpredictable) solar energy generation, relaxing the capacity constraints (which are currently around 15%) and achieving 100% or greater integration of renewables will require a fundamental transformation of the power grid via the utilization of exponentially larger amounts of AMI enabled fine-grained data. To address the challenges in increasing the penetration of renewable energy based DERs, this project envisions an Enhanced System Layer (ESL) at the distribution network level that is reliable, cost-effective and scalable to millions of Distributed Energy Resources (DERs)/devices. This includes developing: 1) Transformative and highly scalable machine learning based predictive analytics tools that plug into distribution system planning and provide real-time situational awareness at the distribution level for short and long-term operational planning. The tools will be built using novel data-driven energy models of millions of active nodes with AMI, 2) Adaptive stochastic analysis and optimization algorithms for real-time grid operations, 3) Dynamic Scenario Analysis using parallel Cloudenabled implementations with < 1 minute computational cycle times.

14 SOLAR ENERGY↗