2,814 research outputs found
Teacher-apprentices RL (TARL): leveraging complex policy distribution through generative adversarial hypernetwork in reinforcement learning
No full textTypically, a Reinforcement Learning (RL) algorithm focuses in learning a single deployable policy as the end product. Depending on the initialization methods and seed randomization, learning a single policy could possibly leads to convergence to different local optima across different runs, especially when the algorithm is sensitive to hyper-parameter tuning. Motivated by the capability of Generative Adversarial Networks (GANs) in learning complex data manifold, the adversarial training procedure could be utilized to learn a population of good-performing policies instead. We extend the teacher-student methodology observed in the Knowledge Distillation field in typical deep neural network prediction tasks to RL paradigm. Instead of learning a single compressed student network, an adversarially-trained generative model (hypernetwork) is learned to output network weights of a population of good-performing policy networks, representing a school of apprentices. Our proposed framework, named Teacher-Apprentices RL (TARL), is modular and could be used in conjunction with many existing RL algorithms. We illustrate the performance gain and improved robustness by combining TARL with various types of RL algorithms, including direct policy search Cross-Entropy Method, Q-learning, Actor-Critic, and policy gradient-based methods.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Interactive Intelligenc
BADDr: Bayes-Adaptive Deep Dropout RL for POMDPs
No full textWhile reinforcement learning (RL) has made great advances in scalability, exploration and partial observability are still active research topics. In contrast, Bayesian RL (BRL) provides a principled answer to both state estimation and the exploration-exploitation trade-off, but struggles to scale. To tackle this challenge, BRL frameworks with various prior assumptions have been proposed, with varied success. This work presents a representation-agnostic formulation of BRL under partially observability, unifying the previous models under one theoretical umbrella. To demonstrate its practical significance we also propose a novel derivation, Bayes-Adaptive Deep Dropout rl (BADDr), based on dropout networks. Under this parameterization, in contrast to previous work, the belief over the state and dynamics is a more scalable inference problem. We choose actions through Monte-Carlo tree search and empirically show that our method is competitive with state-of-the-art BRL methods on small domains while being able to solve much larger ones.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Interactive Intelligenc
Refined Risk Management in Safe Reinforcement Learning with a Distributional Safety Critic
No full textSafety is critical to broadening the real-world use of reinforcement learning (RL). Modeling the safety aspects using a safety-cost signal separate from the reward is becoming standard practice, since it avoids the problem of finding a good balance between safety and performance. However, the total safety-cost distribution of different trajectories is still largely unexplored. In this paper, we propose an actor critic method for safe RL that uses an implicit quantile network to approximate the distribution of accumulated safety-costs. Using an accurate estimate of the distribution of accumulated safetycosts, in particular of the upper tail of the distribution, greatly improves the performance of riskaverse RL agents. The empirical analysis shows that our method achieves good risk control in complex safety-constrained environments.AlgorithmicsIntelligent Electrical Power Grid
qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation
No full textCompiling a quantum circuit for specific quantum hardware is a challenging task. Moreover, current quantum computers have severe hardware limitations. To make the most use of the limited resources, the compilation process should be optimized. To improve currents methods, Reinforcement Learning (RL), a technique in which an agent interacts with an environment to learn complex policies to attain a specific goal, can be used. In this work, we present qgym, a software framework derived from the OpenAI gym, together with environments that are specifically tailored towards quantum compilation. The goal of qgym is to connect the research fields of Artificial Intelligence (AI) with quantum compilation by abstracting parts of the process that are irrelevant to either domain. It can be used to train and benchmark RL agents and algorithms in highly customizable environments.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Quantum Circuit Architectures and Technolog
Influence-Augmented Local Simulators: a Scalable Solution for Fast Deep RL in Large Networked Systems
No full textLearning effective policies for real-world problems is still an open challenge for the field of reinforcement learning (RL). The main limitation being the amount of data needed and the pace at which that data can be obtained. In this paper, we study how to build lightweight simulators of complicated systems that can run sufficiently fast for deep RL to be applicable. We focus on domains where agents interact with a reduced portion of a larger environment while still being affected by the global dynamics. Our method combines the use of local simulators with learned models that mimic the influence of the global system. The experiments reveal that incorporating this idea into the deep RL workflow can considerably accelerate the training process and presents several opportunities for the future.Interactive IntelligenceAlgorithmic
Expression of the androgen receptor and its association with disease outcome in breast cancer
No full textAbstractMurphy N, Bianco-Miotto T, Ricciardelli C, Ruiz AI, Segara D, McNeil CM, Crea P, Henshall SM, Birrell SN, Butler LM, Sutherland RL, Tilley WD
Functional and association analysis of an Amerindian-derived population-specific p.(Thr280Met) variant in RBPJL, a component of the PTF1 complex
No full textPTF1 complex is critical for pancreatic development and maintenance of adult exocrine pancreas. As a part of our ongoing studies to identify genetic variation that contributes to type 2 diabetes (T2D) in American Indians, we analyzed variation in genes that form this complex, namely PTF1A, RBPJ, and its paralogue RBPJL. A c.839C>T (p.(Thr280Met)) variant (rs200998587:C>T, risk allele frequency = 0.03) in RBPJL, identified only in Amerindian-derived populations, associated with T2D (OR = 1.60[1.21-2.13] per Met allele, P = 0.001) and age of diabetes onset (HR = 1.40[1.14-1.72], P = 0.001). Knockdown of Rbpjl in mouse pancreatic acinar cells resulted in a significant decrease in the mRNA expression of genes encoding exocrine enzymes including Ctrb. CTRB1/2 is an established T2D locus where the protective allele associates with increased GLP-1-stimulated insulin secretion and higher expression of CTRB1/2. In vitro studies show that cells expressing the Met280 allele had lower RBPJL protein levels than cells expressing the Thr280 allele, despite having comparable levels of RNA, suggesting that the Met280 RBPJL is less stable. Additionally, luciferase assays in HEK293 cells which examined two different RBPJL responsive promoters, including the promoter for CTRB1, also identified reduced transactivation by the Met280 RBPJL. Similarly, overexpression of both Met280 and Thr280 RBPJL in mouse pancreatic acinar cells identified a significant impairment in the expression of Cel when transactivated by the Met280 RBPJL. In summary, we identified a functional, Amerindian-derived population-specific c.839C>T (p.(Thr280Met)) variant in the pancreas specific RBPJL that may modify T2D risk by regulating exocrine enzyme expression
Use of artemether-lumefantrine in the treatment of asymptomatic-malaria infection in HIV-positive and HIVnegative Nigerian adults.
No full textMalaria /HIV co-infection is a major challenge to public health in developing countries and yet
potential drug-drug interactions between antimalarial and antiviral regimens have not been
adequately investigated in people with both HIV and Plasmodium falciparum infections. Earlier
studies on the use of artemether-lumefantrine (AL) in Nigeria have neither addressed its use in
HIV-positive subjects nor in asymptomatic-malaria infection.
The present study investigated associations between drug resistant P. falciparum and the use
of medication for HIV management, drug-drug interactions between artemether-lumefantrine
and antiretroviral drugs (ARV) and the molecular markers of artemether-lumefantrine and
other antimalarial drugs.
Results of the study revealed an elevated day 7 lumefantrine concentrations in HIV subjects on
nevirapine treatment compared to their HIV-negative counterparts. Associations between
elevated day 7 levels of lumefantrine and the persistent parasitaemia could not be evaluated
due to inadequate power. Genetic analysis by DNA sequence of P. falciparum isolates revealed
strong selection for the pfmdr1codon86N allele among all treated individuals. This
polymorphism is a strong indicator of AL treatment failure or slow clearance in vivo. There was
a 72.6% prevalence of the pfcrt76T mutations in the population and this was observed to be
higher in the HIV-positive subjects. Three new mutations F73S, S97L and G165R were detected
on the pfmdr1 gene and the first case S436F mutation on the pfdhps gene to be reported in
Nigeria. The dhpsK540E and dhfrI164L mutations, associated with high-level resistance to
sulfadoxine-pyrimethamine (SP) were not observed in our small sample size.
The study also revealed that HIV-positive subjects were more likely to harbour parasites, at a
higher density, before and after treatment. Improvement of the immune status of HIV-infected
patients was suggested by the increase of CD4 cell count level in about 68% of the HIV-positive
patients.
This is a preliminary study and first of its kind to investigate drug-drug interactions between
ARVs and the antimalarial drug AL in HIV-positive patients co-infected with P. falciparum in
relation to parasite clearance. The findings of the study are very important but more work is
urgently needed with a larger sample size to confirm these findings
Subtask-masked curriculum learning for reinforcement learning with application to UAV maneuver decision-making
No full textUnmanned Aerial Vehicle (UAV) maneuver strategy learning remains a challenge when using Reinforcement Learning (RL) in this sparse reward task. In this paper, we propose Subtask-Masked curriculum learning for RL (SUBMAS-RL), an efficient RL paradigm that implements curriculum learning and knowledge transfer for UAV maneuver scenarios involving multiple missiles. First, this study introduces a novel concept known as subtask mask to create source tasks from a target task by masking partial subtasks. Then, a subtask-masked curriculum generation method is proposed to generate a sequenced curriculum by alternately conducting task generation and task sequencing. To establish efficient knowledge transfer and avoid negative transfer, this paper employs two transfer techniques, policy distillation and policy reuse, along with an explicit transfer condition that masks irrelevant knowledge. Experimental results demonstrate that our method achieves a 94.8% success rate in the UAV maneuver scenario, where the direct use of reinforcement learning always fails. The proposed RL framework SUBMAS-RL is expected to learn an effective policy in complex tasks with sparse rewards.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Algorithmic
Reinforcement Learning for Intelligent Healthcare Systems: A Review of Challenges, Applications, and Open Research Issues
No full textThe rise of chronic disease patients and the pandemic pose immediate threats to healthcare expenditure and mortality rates. This calls for transforming healthcare systems away from one-on-one patient treatment into intelligent health systems, leveraging the recent advances of Internet of Things and smart sensors. Meanwhile, reinforcement learning (RL) has witnessed an intrinsic breakthrough in solving a variety of complex problems for distinct applications and services. Thus, this article presents a comprehensive survey of the recent models and techniques of RL that have been developed/used for supporting Intelligent-healthcare (I-health) systems. It can guide the readers to deeply understand the state-of-the-art regarding the use of RL in the context of I-health. Specifically, we first present an overview of the I-health systems' challenges, architecture, and how RL can benefit these systems. We then review the background and mathematical modeling of different RL, deep RL (DRL), and multiagent RL models. We highlight important guidelines on how to select the appropriate RL model for a given problem, and provide quantitative comparisons, showing the results of deploying key RL models in two scenarios that can be followed in monitoring applications. After that, we conduct an in-depth literature review on RL's applications in I-health systems, covering edge intelligence, smart core network, and dynamic treatment regimes. Finally, we highlight emerging challenges and future research directions to enhance RL's success in I-health systems, which opens the door for exploring some interesting and unsolved problems.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Networked System
- …
