Engineering Commons^™

A Study Of Deep Reinforcement Learning In Autonomous Racing Using Deepracer Car, Mukesh Ghimire

Honors Theses

Reinforcement learning is thought to be a promising branch of machine learning that has the potential to help us develop an Artificial General Intelligence (AGI) machine. Among the machine learning algorithms, primarily, supervised, semi supervised, unsupervised and reinforcement learning, reinforcement learning is different in a sense that it explores the environment without prior knowledge, and determines the optimal action. This study attempts to understand the concept behind reinforcement learning, the mathematics behind it and see it in action by deploying the trained model in Amazon's DeepRacer car. DeepRacer, a 1/18^th scaled autonomous car, is the agent which is trained …

Landing Throttleable Hybrid Rockets With Hierarchical Reinforcement Learning In A Simulated Environment, Francesco Alessandro Stefano Mikulis-Borsoi

Honors Theses and Capstones

In this paper, I develop a hierarchical Markov Decision Process (MDP) structure for completing the task of vertical rocket landing. I start by covering the background of this problem, and formally defining its constraints. In order to reduce mistakes while formulating different MDPs, I define and develop the criteria for a standardized MDP definition format. I then decompose the problem into several sub-problems of vertical landing, namely velocity control and vertical stability control. By exploiting MDP coupling and symmetrical properties, I am able to significantly reduce the size of the state space compared to a unified MDP formulation. This paper …

A Comparative Analysis Of Reinforcement Learning Applied To Task-Space Reaching With A Robotic Manipulator With And Without Gravity Compensation, Jonathan Fugal

Theses and Dissertations--Electrical and Computer Engineering

Advances in computing power in recent years have facilitated developments in autonomous robotic systems. These robotic systems can be used in prosthetic limbs, wearhouse packaging and sorting, assembly line production, as well as many other applications. Designing these autonomous systems typically requires robotic system and world models (for classical control based strategies) or time consuming and computationally expensive training (for learning based strategies). Often these requirements are difficult to fulfill. There are ways to combine classical control and learning based strategies that can mitigate both requirements. One of these ways is to use a gravity compensated torque control with reinforcement …

Utilizing Trajectory Optimization In The Training Of Neural Network Controllers, Nicholas Kimball

Master's Theses

Applying reinforcement learning to control systems enables the use of machine learning to develop elegant and efficient control laws. Coupled with the representational power of neural networks, reinforcement learning algorithms can learn complex policies that can be difficult to emulate using traditional control system design approaches. In this thesis, three different model-free reinforcement learning algorithms, including Monte Carlo Control, REINFORCE with baseline, and Guided Policy Search are compared in simulated, continuous action-space environments. The results show that the Guided Policy Search algorithm is able to learn a desired control policy much faster than the other algorithms. In the inverted pendulum …

Neuron Clustering For Mitigating Catastrophic Forgetting In Supervised And Reinforcement Learning, Benjamin Frederick Goodrich

Doctoral Dissertations

Neural networks have had many great successes in recent years, particularly with the advent of deep learning and many novel training techniques. One issue that has affected neural networks and prevented them from performing well in more realistic online environments is that of catastrophic forgetting. Catastrophic forgetting affects supervised learning systems when input samples are temporally correlated or are non-stationary. However, most real-world problems are non-stationary in nature, resulting in prolonged periods of time separating inputs drawn from different regions of the input space.

Reinforcement learning represents a worst-case scenario when it comes to precipitating catastrophic forgetting in neural networks. …