Skip to content
View proxymallick's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report proxymallick

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
proxymallick/README.md

Prakash Mallick's Short Bio

Introduction

Hi, I’m Prakash Mallick, a researcher with a passion for topics related to control theory, machine learning, robotics, quantitative finance and data structures.

Professional Experience

Machine Learning Researcher, AIML, Defence Science and Technology Group (DSTG)

  • Currently a postdoctoral researcher at AIML, working with DSTG on producing capabilities at the intersection of machine learning and signal processing for real-time security and surveillance.
  • Focus on analyzing RF spectrum to detect, identify, and generate models that can learn and generalize in real-time for out-of-distribution data.

Quantitative Researcher/Engineer, Ardea Investment Management

  • Worked as a quantitative researcher/engineer in the Research team at Ardea Investment Management.
  • Collaborated with academics, economists, portfolio managers, and research analysts to deliver market-leading analysis for clients.
  • Utilized statistical and machine learning research, computing expertise, and state-of-the-art optimization models to develop business tools and perform complex data analysis.
  • Developed and implemented performant machine learning algorithms to deliver solutions to client requests.

Ph.D. Research in Electrical Engineering, University of Newcastle, Australia

  • Graduated with a Ph.D. in Electrical Engineering, specializing in the intersection of optimal control theory and machine learning, specifically reinforcement learning applied to unknown dynamical systems, mainly in robotic applications.
  • Carried out research on estimating control signal parameters in the presence of measurement noise, resulting in optimal policy with reduced uncertainty and better learning in model-based reinforcement learning frameworks.

Development of Neuro-Prosthetics, Department of Mechanical Engineering

  • Contributed to the development of neuro-prosthetics for amputees in the Department of Mechanical Engineering.
  • Worked on postural synergy modeling and control algorithms for an Allegro robotic hand.
  • Featured on various Australian news channels for the work done: Link to video.

Electrical Excavation Engineer, Coal India Limited

  • Worked as an electrical excavation engineer at Coal India Limited.
  • Optimized production processes using operations research concepts, resulting in reduced machinery usage, downtime, increased productivity, and cost savings.
  • Developed mine plans prioritizing safety, efficiency, and cost-effectiveness through simulation modeling.
  • Provided training and support for efficient operation of heavy engineering equipment like dumpers, loaders, and cranes.

Education

  • Ph.D. in Electrical Engineering from University of Newcastle, Australia in 2022
    • Research focused on optimal control theory and machine learning applied to unknown dynamical systems, mainly in robotic applications.
    • Worked on estimating parameters of control signals when the system has measurement noise to achieve optimal policy with reduced uncertainty and better learning when embedded in a model-based reinforcement learning framework.
  • Masters of Engineering in Mechatronics from University of Melbourne in 2017
    • Introduced to the world of applied maths and operations research which led me to pursue a Ph.D. in optimisation and machine learning.
  • Electrical Engineering from National Institute of Technology, Rourkela in 2012

Skills and Expertise

  • Linear and non-linear control theory
  • System identification
  • Supervised learning
  • Deep reinforcement learning
  • Stochastic optimal control
  • Probabilistic inference
  • Dynamics of robots
  • Algorithms
  • Data structures

Thank you for visiting my GitHub profile! Feel free to check out my repositories and projects, and don't hesitate to contact me for any questions or collaboration opportunities.

Popular repositories Loading

  1. EM-Guided-Policy-Search EM-Guided-Policy-Search Public

    Sample efficient learning using expectation maximization

    Python 2

  2. OpenDet_CWA OpenDet_CWA Public

    Open-set detection using Wasserstein Distance and Spectral Normalisation

    Python 2

  3. Model-Based-RL-Gazebo-Robosuite Model-Based-RL-Gazebo-Robosuite Public

    Reinforcement Learning training task on UR5e Gazebo simulation

    Makefile 1

  4. rllab rllab Public

    Forked from cbfinn/rllab

    rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

    Python

  5. gps gps Public

    Forked from cbfinn/gps

    Guided Policy Search

    Python

  6. phd-bibliography phd-bibliography Public

    Forked from eleurent/phd-bibliography

    References on Optimal Control, Reinforcement Learning and Motion Planning