Analyzing optimization landscape of recent policy optimization methods in deep RL

Analyzing optimization landscape of recent policy optimization methods in deep RL

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022.

Bibliografiska uppgifter
Huvudupphovsmän:	Khan, Mahir Asaf, Ashraf, Adib, Amin, Tahmid Adib
Övriga upphovsmän:	Rashid, Warida
Materialtyp:	Lärdomsprov
Språk:	English
Publicerad:	Brac University 2023
Ämnen:	Optimization landscape Policy optimization Deep reinforcement learning Variance reduction Control variates Cognitive learning theory Machine learning
Länkar:	http://hdl.handle.net/10361/18306

Liknande verk

Implementation of reinforcement learning architecture to augment an AI that can self-learn to play video games
av: Mahmud, Aqil, et al.
Publicerad: (2023)

ROBB: recurrent proximal policy optimization reinforcement learning for optimal block formation in bitcoin blockchain network
av: Dutta, Amit
Publicerad: (2024)

Combinatorial optimization : algorithms and complexity /
av: Papadimitriou, Christos H.
Publicerad: (1998)

Convex optimization /
av: Boyd, Stephen P.
Publicerad: (2004)

Self-learning game bot using deep reinforcement learning
av: Ananto, Azizul Haque
Publicerad: (2018)

Optimal energy rendering approach from lightning return stroke
av: Chowdhury, A.S.M. Mishkat Hussain, et al.
Publicerad: (2016)

Elements of dynamic optimization /
av: Chiang, Alpha C., 1927-
Publicerad: (1992)

Elements of dynamic optimization /
av: Chiang, Alpha C., 1927-
Publicerad: (2012)

Convex optimization /
av: Boyd, Stephen P.
Publicerad: (1994)

Optimizing compilers for modern architectures : a dependence-based approach /
av: Allen, Randy
Publicerad: (2001)

Implementation of real-time learning on homomorphically encrypted visual inputs
av: Bhuiyan, Emtiaz MD Tafsir, et al.
Publicerad: (2021)

Optimal capacitor placement in radial distribution system for loss minimization using particle swarm optimization
av: Ismail, Abdiwahab Mohamed
Publicerad: (2024)

Early stage detection and classification of colon cancer using deep learning and explainable AI on histopathological images
av: Hossain, Mainul, et al.
Publicerad: (2022)

Character animation using reinforcement learning and imitation learning algorithms
av: Tahmid, Tokey, et al.
Publicerad: (2021)

Traﬃc congestion reduction in SUMO using reinforcement learning method
av: Mouly, Radia Rahman, et al.
Publicerad: (2021)

Skin cancer detection and classification using multiple optimized deep convolutional neural network
av: Sakir, Adnan, et al.
Publicerad: (2023)

Applied shape optimization for fluids
av: Mohammadi, B.

Dynamic power management by reinforcement learning
av: Hossain, Safayet, et al.
Publicerad: (2016)

Accelerating ant colony optimization by using local search
av: Tabassum, Nabila, et al.
Publicerad: (2015)

Iterative Methods in Combinatorial Optimization
av: Lap Chi Lau, R. Ravi, Mohit Singh
Publicerad: (2012)

Importance of educational data mining for optimized operations in Brac University
av: Saad, Mohammad Alif Hossain
Publicerad: (2021)

How we learn and why we don't : student survival guide using the cognitive profile inventory /
av: Krause, Lois Breur
Publicerad: (2008)

An efficient deep learning approach to detect skin Cancer
av: Islam, Ashfaqul, et al.
Publicerad: (2022)

Mechanism Design
av: Rakesh V. Vohra
Publicerad: (2013)

Yoga posture recognition using the deep learning process
av: Islam, Abidul, et al.
Publicerad: (2023)

ShopUp: transforming business through product optimization
av: Tamim, Farhad Hassan
Publicerad: (2018)

Reinforcement learning : an introduction /
av: Sutton, Richard S., et al.
Publicerad: (2018)

Resource optimization in cloud computing using dynamic load balancing technique
av: Rafid, Mutasim, et al.
Publicerad: (2021)

Reinforcement learning based electricity price forecasting in Blockchain based smart grid environment
av: Moti, Md Mahraj Murshalin Al, et al.
Publicerad: (2021)

Real-time mastitis detection in livestock using deep learning and machine learning leveraging edge devices
av: Ghosh, Kawshik Kumar, et al.
Publicerad: (2023)

A conventional & deep learning strategy for analyzing & detecting Bengali fake news in online medium
av: Ahmed, Istiak, et al.
Publicerad: (2023)

Classification of peripheral blood cell images using deep learning
av: Aadi, Oyshik Ahmed, et al.
Publicerad: (2024)

Importance of Search Engine Optimization (SEO) for businesses in Bangladesh
av: Chishty, Wadud
Publicerad: (2018)

Essentials of learning : the new cognitive learning for students of education /
av: Travers, Robert Morris William, 1913-

Resource-aware task scheduling by an adversarial bandit solver method in wireless sensor networks
av: Khan, Muhidul Islam
Publicerad: (2016)

A modern technique to detect potholes by Computer Vision and Deep Learning
av: Saif, Muntasir Mahmud, et al.
Publicerad: (2023)

Corn leaf disease detection using deep convolution neural network
av: Rabbi, Rawhatur, et al.
Publicerad: (2023)

Prospect Theory
av: Peter P. Wakker
Publicerad: (2012)

Method optimization for isolation of Klebsiella Bacteriophage from soil samples
av: Khan, Zumana Hayat
Publicerad: (2021)

Reinforcement learning based autonomous vehicle for exploration and exploitation of undiscovered track
av: Issa, Razin Bin, et al.
Publicerad: (2020)