Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 77 for “"Reinforcement learning (Machine learning)"”.

  1. Discovering hierarchy in reinforcement learning

    … discovering hierarchical structure in reinforcement learning. Current algorithms for reinforcement learning fail to scale as problems become more complex. Many complex environments empirically exhibit hierarchy and can be modeled as interrelated subsystems, each in turn with hierarchic …

    unsw Repository record for Discovering hierarchy in reinforcement learning (opens in a new tab)

  2. Adaptive representations for reinforcement learning

    In reinforcement learning, an autonomous agent seeks an effective control policy for tackling a sequential decision task. Unlike in supervised learning, the agent never sees examples of correct or incorrect behavior but receives only a reward signal as feedback. One limitation of current methods is …

    texas Repository record for Adaptive representations for reinforcement learning (opens in a new tab)

  3. Learning Control Policies for Fall Prevention and Safety in Bipedal Locomotion

    … this thesis, to address these issues we develop learning-based algorithms capable of synthesizing push recovery control policies for two different kinds of robots : Humanoid robots and assistive robotic devices that assist in bipedal locomotion. Our work can be branched into two closely related …

    gatech Repository record for Learning Control Policies for Fall Prevention and Safety in Bipedal Locomotion (opens in a new tab)

  4. Online statistical modeling in reinforcement learning

    … against a model can greatly improve the learning rate of Reinforcement Learning. The Dyna algorithm uses both real experience and model learning to facilitate simulation. However, the model used in Dyna is fairly limited, yet still has some desirable properties. Examination of a few …

    ttu Repository record for Online statistical modeling in reinforcement learning (opens in a new tab)

  5. Reinforcement learning in the control of a simulated life support system

    … control strategies for an ALS system. Reinforcement learning (RL) is a machine learning technique that finds effective control strategies. RL does this by interacting with the environment, and has been used successfully to control systems with noisy inputs and stochastic actions. RL …

    ttu Repository record for Reinforcement learning in the control of a simulated life support system (opens in a new tab)

  6. PRESCRIPTIVE ANALYTICS WITH INTERNET OF THINGS

    … in Industry 4.0. The connectivity of physical machines and smart digital technologies promises various efficiency with autonomous capabilities. Prescriptive analytics is one of the solutions required in the creation of these intelligent systems and the focus of this topic. This thesis has …

    nus Repository record for PRESCRIPTIVE ANALYTICS WITH INTERNET OF THINGS (opens in a new tab) Download file for PRESCRIPTIVE ANALYTICS WITH INTERNET OF THINGS (opens in a new tab)

  7. APPLY MACHINE LEARNING MODELS AS CLINICAL DECISION SUPPORT TOOLS TO ASSIST CLINICIAN'S DECISION MAKING

    … due to a few reasons. Unlike typical supervised learning tasks, the ground truth of many healthcare tasks are unknown. Besides, many clinical guidelines provide one-size-fits-all recommendations, but do not personalize treatment for different patients. In addition, clinicians' demonstrations can …

    nus Repository record for APPLY MACHINE LEARNING MODELS AS CLINICAL DECISION SUPPORT TOOLS TO ASSIST CLINICIAN'S DECISION MAKING (opens in a new tab) Download file for APPLY MACHINE LEARNING MODELS AS CLINICAL DECISION SUPPORT TOOLS TO ASSIST CLINICIAN'S DECISION MAKING (opens in a new tab)

  8. Dynamic pricing for airline ancillaries with customer context

    … booking website. We show that traditional machine learning techniques outperform human rule-based approaches in an online setting by improving conversion by 36% and revenue per offer by 10%. We also provide results for our offline experiments which show that deep learning algorithms …

    uiuc Repository record for Dynamic pricing for airline ancillaries with customer context (opens in a new tab)

  9. Using Reinforcement Learning in Partial Order Plan Space

    … efficiency. In this thesis, I discuss applying a reinforcement learning method, called First-visit Monte Carlo method, to partial order planning in order to design agents which do not need any training data or heuristics but are still able to make informed decisions in plan space based on …

    unt Repository record for Using Reinforcement Learning in Partial Order Plan Space (opens in a new tab)

  10. An echo state model of non-Markovian reinforcement learning

    … must exhibit the Markov property in order for reinforcement learning to be applicable. Empirical evidence, however, suggests that reinforcement learning also applies to domains where the state-action space is approximately Markovian, a requirement for the overwhelming majority of real-world …

    colostate Repository record for An echo state model of non-Markovian reinforcement learning (opens in a new tab)

  11. Hluboké neuronové sítě pro posilované učení

    Cílem této práce je použití hlubokých neuronových sítí na problém v posilovaném učení. Používám moji úpravu 2D hry Tuxánci jako testovací prostředí. Jedná se o úpravu, která zajišťuje možnosti využití hry jako prostředí pro strojového učení. Následně řeším problémy s naučením agenta pomocí …

    brno-tech Repository record for Hluboké neuronové sítě pro posilované učení (opens in a new tab)

  12. Hluboké neuronové sítě pro posilované učení

    Práce popisuje trénovací prostředí pro trénování postavičky chodící po dvou končetinách. Prostředí je implementováno v AI Gym pomocí fyzikálního modelu PyBullet. Úlohy z prostředí jsou řešené pomocí posilovaného učení algoritmem ActorCritic. Každá z úloh je zaměřená na základní pohyby postavičky. …

    brno-tech Repository record for Hluboké neuronové sítě pro posilované učení (opens in a new tab)

  13. From Human Behavior to Machine Behavior

    … and computational resources, the development of machine learning algorithms for duplicating human cognitive abilities has made rapid progress. To solve difficult scenarios, learning-based methods must search for solutions in a predefined but large space. Along with implementing a smart …

    ucf Repository record for From Human Behavior to Machine Behavior (opens in a new tab)

  14. Reinforcement Learning: Low Discrepancy Action Selection for Continuous States and Actions

    In reinforcement learning the process of selecting an action during the exploration or exploitation stage is difficult to optimize. The purpose of this thesis is to create an action selection process for an agent by employing a low discrepancy action selection (LDAS) method. This should allow the …

    gsu Repository record for Reinforcement Learning: Low Discrepancy Action Selection for Continuous States and Actions (opens in a new tab)

  15. Aplikace posilovaného učení při řízení modelu vozidla

    … agenta je řízeno pomocí posilovaného učení (reinforcement learning) s využitím neuronových sítí. Agent získává snímky z přední kamery vozidla a na základě jejich interpretace vybírá vhodné akce pro řízení vozidla. V rámci práce jsem navrhl několik funkcí odměn a s vytvořenými modely jsem …

    brno-tech Repository record for Aplikace posilovaného učení při řízení modelu vozidla (opens in a new tab)

Page 1 of 4