Implementation of reinforcement learning architecture to augment an AI that can self-learn to play video games

Implementation of reinforcement learning architecture to augment an AI that can self-learn to play video games

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.

Bibliografiske detaljer
Main Authors:	Mahmud, Aqil, Khan, Aswat Karim, Hasan Rafi, Mohammad Mehdi, Fahim, Kazi Rayhan
Andre forfattere:	Rasel, Annajiat Alim
Format:	Thesis
Sprog:	English
Udgivet:	Brac University 2023
Fag:	Reinforcement learning Neural networks Games AI Proximal policy optimization Reinforcement learning.
Online adgang:	http://hdl.handle.net/10361/19954

Lignende værker

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

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

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

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

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

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

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

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

Reinforcement learning based autonomic virtual machine management in clouds
af: Habib, Arafat, et al.
Udgivet: (2018)

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

Analyzing optimization landscape of recent policy optimization methods in deep RL
af: Khan, Mahir Asaf, et al.
Udgivet: (2023)

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

Exploring the applications of deep reinforcement learning and quantum variational circuit In quantum machine learning
af: Saha, Prashanta Kumar, et al.
Udgivet: (2021)

Carbon reinforced epoxy systems /
Udgivet: (1974)

Enhancing object clarity in single channel night vision images using deep reinforcement learning
af: Hossain, Adil, et al.
Udgivet: (2021)

Approval VO#13 adjustment unit price for planting reinforcement work
af: Brac University
Udgivet: (2023)

Unit price approval-planting reinforcing works
af: WOHA Designs PTE LTD, et al.
Udgivet: (2023)

Adjustment unit price for planting reinforcement work of BRAC University new campus project
af: BUCG-ABC Joint Venture (BUCG-ABC JV)
Udgivet: (2023)

UAV assisted cooperative caching on network edge using multi agent Actor critic reinforcement learning
af: Araf, Sadman, et al.
Udgivet: (2021)

Regarding the effect of zone C earth excavation on reinforcement approach
af: BUCG-ABC Joint Venture (BUCG-ABC JV)
Udgivet: (2023)

Design of concrete structures /
af: Nilson, Arthur H.
Udgivet: (2004)

Health trauma and well-being assistant for Bengali seniors in household: a multimodal approach
af: Islam, Md. Nazmul, et al.
Udgivet: (2024)

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

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

Implementation of neural network in game engine to create smart bot and behavior analysis
af: Shovon, Zamshed Khan, et al.
Udgivet: (2018)

Malicious data classification in packet data network through hybrid meta deep learning
af: Tapu, Sakib Uddin, et al.
Udgivet: (2023)

Leadership games : experiential learning for organizational development /
af: Kaagan, Stephen S.
Udgivet: (1999)

Personalization in federated recommendation system using SVD++ with explainability
af: Patwary, Kabbya Kantam, et al.
Udgivet: (2022)

Real-time foul detection in football matches using machine learning techniques
af: Siddiqui, Bishal Sadi, et al.
Udgivet: (2024)

Behavior change analysis due to violent video gaming using deep learning models
af: Rahman, Akhlak Ur, et al.
Udgivet: (2024)

Resource aware task scheduling in wireless sensor networks
af: Mahjabeen, Maksura
Udgivet: (2016)

A hybrid deep learning model and explainable AI-based Bengali hate speech multi-label classification and interpretation
af: Shakil, Mahmudul Hasan
Udgivet: (2023)

Let's play Asian children's games /
Udgivet: (1978)

How traditional games play a role in connecting children to their culture, identity and self
af: Shatil, Tanvir
Udgivet: (2023)

Virtual for real: massively multiplayer online role playing game and the development of L2 communication skills in young learners
af: Akther, Kohinoor
Udgivet: (2023)

IoT based air components collection for machine learning reinforcement
af: Islam, Tanjima, et al.
Udgivet: (2024)

Predicting obesity: a comparative analysis of machine learning models incorporating different features
af: Rahman, Md.Sakibur, et al.
Udgivet: (2023)

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

Micro-learning modules are linked to enhanced retention of the learners and can be geared toward subconscious knowledge acquisition in an organization
af: Siddique, Noman
Udgivet: (2024)

Self-direction for lifelong learning : a comprehensive guide to theory and practice /
af: Candy, Philip C.
Udgivet: (1991)