Tag Archives: Reinforcement Learning

On the extended use of RL for navigation in UAVs

November 3, 2023 10:07 ,

Fadi AlMahamid, Katarina Grolinger, Autonomous Unmanned Aerial Vehicle navigation using Reinforcement Learning: A systematic review, Engineering Applications of Artificial Intelligence, Volume 115, 2022 DOI: 10.1016/j.engappai.2022.105321.

There is an increasing demand for using Unmanned Aerial Vehicle (UAV), known as drones, in different applications such as packages delivery, traffic monitoring, search and rescue operations, and military combat engagements. In all of these applications, the UAV is used to navigate the environment autonomously \u2014 without human interaction, perform specific tasks and avoid obstacles. Autonomous UAV navigation is commonly accomplished using Reinforcement Learning (RL), where agents act as experts in a domain to navigate the environment while avoiding obstacles. Understanding the navigation environment and algorithmic limitations plays an essential role in choosing the appropriate RL algorithm to solve the navigation problem effectively. Consequently, this study first identifies the main UAV navigation tasks and discusses navigation frameworks and simulation software. Next, RL algorithms are classified and discussed based on the environment, algorithm characteristics, abilities, and applications in different UAV navigation problems, which will help the practitioners and researchers select the appropriate RL algorithms for their UAV navigation use cases. Moreover, identified gaps and opportunities will drive UAV navigation research.

Posted in: Applications of reinforcement learning to robots , Tagged: , , ,

Survey on RL applied to cyber-security

October 27, 2023 06:19 ,

Amrin Maria Khan Adawadkar, Nilima Kulkarni, Cyber-security and reinforcement learning \u2014 A brief survey, Engineering Applications of Artificial Intelligence, Volume 114, 2022, DOI: 10.1016/j.engappai.2022.105116.

This paper presents a comprehensive literature review on Reinforcement Learning (RL) techniques used in Intrusion Detection Systems (IDS), Intrusion Prevention Systems (IPS), Internet of Things (IoT) and Identity and Access Management (IAM). This study reviews scientific documents such as journals and articles, from 2010 to 2021, extracted from the Science Direct, ACM, IEEEXplore, and Springer database. Most of the research articles published in 2020 and 2021, for cybersecurity and RL are for IDS classifiers and resource optimization in IoTs. Some datasets used for training RL-based IDS algorithms are NSL-KDD, CICIDS, and AWID. There are few datasets and publications for IAM. The few that exist focus on the physical layer authentication. The current state of the art lacks standard evaluation criteria, however, we have identified parameters like detection rate, precision, and accuracy which can be used to compare the algorithms employing RL. This paper is suitable for new researchers, students, and beginners in the field of RL who want to learn about the field and identify problem areas.

Posted in: Computer vision , Tagged: ,

Unexpected consequences of training smarthome systems with reinforcement learning: effects on human behaviours

October 27, 2023 06:02 ,

S. Suman, A. Etemad and F. Rivest, TPotential Impacts of Smart Homes on Human Behavior: A Reinforcement Learning Approach, IEEE Transactions on Artificial Intelligence, vol. 3, no. 4, pp. 567-580, Aug. 2022 DOI: 10.1109/TAI.2021.3127483.

Smart homes are becoming increasingly popular as a result of advances in machine learning and cloud computing. Devices, such as smart thermostats and speakers, are now capable of learning from user feedback and adaptively adjust their settings to human preferences. Nonetheless, these devices might in turn impact human behavior. To investigate the potential impacts of smart homes on human behavior, we simulate a series of hierarchical-reinforcement learning-based human models capable of performing various activities\u2014namely, setting temperature and humidity for thermal comfort inside a Q-Learning-based smart home model. We then investigate the possibility of the human models\u2019 behaviors being altered as a result of the smart home and the human model adapting to one another. For our human model, the activities are based on hierarchical-reinforcement learning. This allows the human to learn how long it must continue a given activity and decide when to leave it. We then integrate our human model in the environment along with the smart home model and perform rigorous experiments considering various scenarios involving a model of a single human and models of two different humans with the smart home. Our experiments show that with the smart home, the human model can exhibit unexpected behaviors such as frequent changing of activities and an increase in the time required to modify the thermal preferences. With two human models, we interestingly observe that certain combinations of models result in normal behaviors, while other combinations exhibit the same unexpected behaviors as those observed from the single human experiment.

Posted in: Psycho-physiological bases of engineering , Tagged: , ,

Human+machine sequential decision making

October 27, 2023 05:59 ,

Q. Zhang, Y. Kang, Y. -B. Zhao, P. Li and S. You, Traded Control of Human\u2013Machine Systems for Sequential Decision-Making Based on Reinforcement Learning, IEEE Transactions on Artificial Intelligence, vol. 3, no. 4, pp. 553-566, Aug. 2022 DOI: 10.1109/TAI.2021.3127857.

Sequential decision-making (SDM) is a common type of decision-making problem with sequential and multistage characteristics. Among them, the learning and updating of policy are the main challenges in solving SDM problems. Unlike previous machine autonomy driven by artificial intelligence alone, we improve the control performance of SDM tasks by combining human intelligence and machine intelligence. Specifically, this article presents a paradigm of a human\u2013machine traded control systems based on reinforcement learning methods to optimize the solution process of sequential decision problems. By designing the idea of autonomous boundary and credibility assessment, we enable humans and machines at the decision-making level of the systems to collaborate more effectively. And the arbitration in the human\u2013machine traded control systems introduces the Bayesian neural network and the dropout mechanism to consider the uncertainty and security constraints. Finally, experiments involving machine traded control, human traded control were implemented. The preliminary experimental results of this article show that our traded control method improves decision-making performance and verifies the effectiveness for SDM problems.

Posted in: Human-robot interaction , Tagged: ,

Action selection strategy for model-free RL based on neurophysiology

October 6, 2023 08:59 ,

D. Wang, S. Chen, Y. Hu, L. Liu and H. Wang, Behavior Decision of Mobile Robot With a Neurophysiologically Motivated Reinforcement Learning Model, IEEE Transactions on Cognitive and Developmental Systems, vol. 14, no. 1, pp. 219-233, March 2022 DOI: 10.1109/TCDS.2020.3035778.

Online model-free reinforcement learning (RL) approaches play a crucial role in coping with the real-world applications, such as the behavioral decision making in robotics. How to balance the exploration and exploitation processes is a central problem in RL. A balanced ratio of exploration/exploitation has a great influence on the total learning time and the quality of the learned strategy. Therefore, various action selection policies have been presented to obtain a balance between the exploration and exploitation procedures. However, these approaches are rarely, automatically, and dynamically regulated to the environment variations. One of the most amazing self-adaptation mechanisms in animals is their capacity to dynamically switch between exploration and exploitation strategies. This article proposes a novel neurophysiologically motivated model which simulates the role of medial prefrontal cortex (MPFC) and lateral prefrontal cortex (LPFC) in behavior decision. The sensory input is transmitted to the MPFC, then the ventral tegmental area (VTA) receives a reward and calculates a dopaminergic reinforcement signal, and the feedback categorization neurons in anterior cingulate cortex (ACC) calculate the vigilance according to the dopaminergic reinforcement signal. Then the vigilance is transformed to LPFC to regulate the exploration rate, finally the exploration rate is transmitted to thalamus to calculate the corresponding action probability. This action selection mechanism is introduced to the actor\u2013critic model of the basal ganglia, combining with the cerebellum model based on the developmental network to construct a new hybrid neuromodulatory model to select the action of the agent. Both the simulation comparison with other four traditional action selection policies and the physical experiment results demonstrate the potential of the proposed neuromodulatory model in action selection.

Posted in: Psycho-physiological bases of engineering , Tagged: ,

Using a physical simulator for sampled rollouts in stochastic optimal control

September 15, 2023 09:47 ,

Carius J, Ranftl R, Farshidian F, Hutter M. Constrained stochastic optimal control with learned importance sampling: A path integral approach, The International Journal of Robotics Research. 2022;41(2):189-209, DOI: 10.1177/02783649211047890.

Modern robotic systems are expected to operate robustly in partially unknown environments. This article proposes an algorithm capable of controlling a wide range of high-dimensional robotic systems in such challenging scenarios. Our method is based on the path integral formulation of stochastic optimal control, which we extend with constraint-handling capabilities. Under our control law, the optimal input is inferred from a set of stochastic rollouts of the system dynamics. These rollouts are simulated by a physics engine, placing minimal restrictions on the types of systems and environments that can be modeled. Although sampling-based algorithms are typically not suitable for online control, we demonstrate in this work how importance sampling and constraints can be used to effectively curb the sampling complexity and enable real-time control applications. Furthermore, the path integral framework provides a natural way of incorporating existing control architectures as ancillary controllers for shaping the sampling distribution. Our results reveal that even in cases where the ancillary controller would fail, our stochastic control algorithm provides an additional safety and robustness layer. Moreover, in the absence of an existing ancillary controller, our method can be used to train a parametrized importance sampling policy using data from the stochastic rollouts. The algorithm may thereby bootstrap itself by learning an importance sampling policy offline and then refining it to unseen environments during online control. We validate our results on three robotic systems, including hardware experiments on a quadrupedal robot.

Posted in: Applications of reinforcement learning to control engineering , Tagged: , ,

Learning rewards from diverse human sources

July 21, 2023 09:46 ,

Bıyık E, Losey DP, Palan M, Landolfi NC, Shevchuk G, Sadigh D., Learning reward functions from diverse sources of human feedback: Optimally integrating demonstrations and preferences, . The International Journal of Robotics Research. 2022;41(1):45-67 DOI: 10.1177/02783649211041652.

Reward functions are a common way to specify the objective of a robot. As designing reward functions can be extremely challenging, a more promising approach is to directly learn reward functions from human teachers. Importantly, data from human teachers can be collected either passively or actively in a variety of forms: passive data sources include demonstrations (e.g., kinesthetic guidance), whereas preferences (e.g., comparative rankings) are actively elicited. Prior research has independently applied reward learning to these different data sources. However, there exist many domains where multiple sources are complementary and expressive. Motivated by this general problem, we present a framework to integrate multiple sources of information, which are either passively or actively collected from human users. In particular, we present an algorithm that first utilizes user demonstrations to initialize a belief about the reward function, and then actively probes the user with preference queries to zero-in on their true reward. This algorithm not only enables us combine multiple data sources, but it also informs the robot when it should leverage each type of information. Further, our approach accounts for the human’s ability to provide data: yielding user-friendly preference queries which are also theoretically optimal. Our extensive simulated experiments and user studies on a Fetch mobile manipulator demonstrate the superiority and the usability of our integrated framework..

Posted in: Applications of reinforcement learning to robots , Tagged: ,

Trying to reach general AI through just decision-making (rewards) instead of using a diversity of paradigms

July 21, 2023 08:37 ,

avid Silver, Satinder Singh, Doina Precup, Richard S. Sutton, Reward is enough, . Artificial Intelligence, Volume 299, 2021 DOI: 10.1016/j.artint.2021.103535.

In this article we hypothesise that intelligence, and its associated abilities, can be understood as subserving the maximisation of reward. Accordingly, reward is enough to drive behaviour that exhibits abilities studied in natural and artificial intelligence, including knowledge, learning, perception, social intelligence, language, generalisation and imitation. This is in contrast to the view that specialised problem formulations are needed for each ability, based on other signals or objectives. Furthermore, we suggest that agents that learn through trial and error experience to maximise reward could learn behaviour that exhibits most if not all of these abilities, and therefore that powerful reinforcement learning agents could constitute a solution to artificial general intelligence.

NOTES:

  • The computational and physical limitations of the agent to cope with a too complex world is the main reason to use learning instead of pre-built knowledge (evolution): it allows the agent to focus on acquiring skills for its own circumstances first, that are the most important for it.
  • Argument why classification (supervised learning) is less powerful and efficient than RL.
  • Same with multi-agent settings vs. one agent confronted with a single complex environment (containing other agents).
Posted in: Psycho-physiological bases of engineering , Tagged: , ,

A nice survey on active learning, in particular for robotics

July 17, 2023 09:10 ,

Annalisa T. Taylor, Thomas A. Berrueta, Todd D. Murphey, Active learning in robotics: A review of control principles, . Mechatronics, Volume 77, 2021 DOI: 10.1016/j.mechatronics.2021.102576.

Active learning is a decision-making process. In both abstract and physical settings, active learning demands
both analysis and action. This is a review of active learning in robotics, focusing on methods amenable to
the demands of embodied learning systems. Robots must be able to learn efficiently and flexibly through
continuous online deployment. This poses a distinct set of control-oriented challenges??one must choose
suitable measures as objectives, synthesize real-time control, and produce analyses that guarantee performance
and safety with limited knowledge of the environment or robot itself. In this work, we survey the fundamental
components of robotic active learning systems. We discuss classes of learning tasks that robots typically
encounter, measures with which they gauge the information content of observations, and algorithms for
generating action plans. Moreover, we provide a variety of examples ?? from environmental mapping to
nonparametric shape estimation ?? that highlight the qualitative differences between learning tasks, information
measures, and control techniques. We conclude with a discussion of control-oriented open challenges, including
safety-constrained learning and distributed learning.

NOTES:

  • RL can be considered one of the areas within computational learning theory, that usually ignore physical embodiment aspects of the learning agent. However, that is only so when RL explores through decision-making, not when it explores randomly, without much purpose of enhancing learning itself through its actions.
  • RL caveats (particularly Deep RL): their large data requirements, lack of generalizability between tasks, as well as their inability to learn incrementally and guarantee
    safety.
  • Bayesian filters can be seen as learner systems: they learn parameters of objects (pose) or environments (maps) aided by some models. However, they are more active learners when they use the robot actions to improve that parameter learning.
  • Gaussian processes can be effective in learning those models when no parameterical form is available or much first-principle knowledge, for instance, when the robot has to learn the model only observing a small part of the environment (local).
  • Entropy/information, Fisher’s information (conditional information) and ergodicity are the main ways of measuring information gain in active learning.
Posted in: Psycho-physiological bases of engineering , Tagged: ,

State of the art of the convergence of Monte Carlo Exploring Starts RL, policy iteration kind, method

July 11, 2023 09:34 ,

Jun Liu, On the convergence of reinforcement learning with Monte Carlo Exploring Starts, . Automatica, Volume 129, 2021 DOI: 10.1016/j.automatica.2021.109693.

A basic simulation-based reinforcement learning algorithm is the Monte Carlo Exploring Starts (MCES) method, also known as optimistic policy iteration, in which the value function is approximated by simulated returns and a greedy policy is selected at each iteration. The convergence of this algorithm in the general setting has been an open question. In this paper, we investigate the convergence of this algorithm for the case with undiscounted costs, also known as the stochastic shortest path problem. The results complement existing partial results on this topic and thereby help further settle the open problem.

Posted in: Reinforcement learning in AI , Tagged: ,