Search Constraints

Start Over
Filtering by: Creator Mishra, Prafulla K. Remove constraint Creator: Mishra, Prafulla K. Advisor Fern, Alan Remove constraint Advisor: Fern, Alan

Search Results

  • Recurrent Neural Networks for Robotic Control of a Human-Scale Bipedal Robot

    Creator:
    Siekmann, Jonah A.
    Abstract:
    Dynamic bipedal locomotion is among the most difficult and yet relevant problems in modern robotics. While a multitude of classical control methods for bipedal locomotion exist, they are often brittle or limited in capability. In recent years, work in applying reinforcement learning to robotics has lead to superior performance across...
    Resource Type:
    Honors College Thesis
    Full Text:
    ://www.worldscientific.com/doi/ abs/10.1142/S0219843604000083. [2] Y. Haikawa K. Hirai, M. Hirose and T. Takenaka. The

  • Practical Reinforcement Learning for Bipedal Locomotion

    Creator:
    Dao, Jeremy
    Abstract:
    Reinforcement learning has emerged as a popular tool for solving control tasks, with multiple works focusing on the complex and dynamic task of locomotion. However, the naive application of reinforcement learning to this problem often produces maladaptive policies that exploit the model or reward function. This results in behavior that...
    Resource Type:
    Capstone Project
    Full Text:
    gradient, we can just perform gradient ascent with some step size α and update the policy parameters: θk

  • Robust Reference-Free Sim-to-Real Reinforcement Learning for Bipedal Locomotion

    Creator:
    Siekmann, Jonah A.
    Abstract:
    In recent years, model-free Deep Reinforcement Learning (RL) has become an increasingly popular alternative to more traditional model-based or optimization-based control methods in solving robotic legged locomotion. However, deploying RL in the real world can be a significant undertaking. Constructing reward functions which compel controllers to learn the desired behavior...
    Resource Type:
    Masters Thesis

  • Investigating Latent State and Uncertainty Representations in Reinforcement Learning

    Creator:
    Koul, Anurag
    Abstract:
    Learning latent space representations of high-dimensional world states has been at the core of recent rapid growth in reinforcement learning(RL). At the same time, RL algo- rithms have suffered from ignored uncertainties in the predicted estimates of model-free or model-based methods. In our work, we investigate both of these aspects...
    Resource Type:
    Dissertation
    Full Text:
    quantization level as k and the dimensions of ĥ and f̂ by Bh and Bf respectively. Based on the above

  • Anomaly Detection: Theory, Explanation and User Feedback

    Creator:
    Siddiqui, Md Amran
    Abstract:
    Anomaly detection has been used in variety of applications in practice, including cyber-security, fraud detection and detecting faults in safety critical systems, etc. Anomaly detectors produce a ranked list of statistical anomalies, which are typically examined by human analysts in order to extract the actual anomalies of interest. Unfortunately, most...
    Resource Type:
    Dissertation
    Full Text:
    for the Three Scoring Methods (IF, AVE, MIN) with Varying Pattern Space Complexity k Over Three