Eskisehir Technical University Info Package Eskisehir Technical University Info Package
  • Info on the Institution
  • Info on Degree Programmes
  • Info for Students
  • Türkçe
About the Program Educational Objectives Key Learning Outcomes Course Structure Diagram with Credits Field Qualifications Matrix of Course& Program Qualifications Matrix of Program Outcomes&Field Qualifications
  • Faculty of Engineering
  • Department of Computer Engineering (English)
  • Course Structure Diagram with Credits
  • Deep Reinforcement Learning
  • Learning Outcomes & Program Qualifications
  • Description
  • Learning Outcomes
  • Course's Contribution to Prog.
  • Learning Outcomes & Program Qualifications
  • ECTS Credit Load
0 : Does not support   1 : Low-level support   2 : Mid-level support   3 : Top level support
Learning Outcomes1234567891011
1. Describe the fundamental concepts and architectures of deep learning.\n1.1. Define the basic structures and components of artificial neural networks.\n1.2. Interpret the operating principles of MLP, RNN/LSTM, and CNN architectures.\n1.3. Develop and implement a simple deep learning model.\n31100000000
2. Identify the fundamental principles of reinforcement learning.\n2.1. Define the core concepts and terminology of reinforcement learning.\n2.2. Distinguish reinforcement learning from supervised learning approaches.31000000000
3. Analyze value-based reinforcement learning methods.\n 3.1. Describe the Q-learning algorithm and its learning mechanism.\n 3.2. Interpret the Deep Q-Network (DQN) approach.\n 3.3. Implement and evaluate a basic DQN agent.-----------
4. Examine policy-based and actor-critic reinforcement learning methods.\n 4.1. Describe the principles of Policy Gradient methods.\n 4.2. Analyze the REINFORCE algorithm and its application.\n 4.3. Interpret the Actor-Critic framework and its components.\n22010000000
5. Compare advanced deep reinforcement learning algorithms.\n 5.1. Compare PPO, SAC, and DDPG algorithms in terms of structure and application.\n 5.2. Evaluate the advantages and limitations of advanced reinforcement learning algorithms.\n22-----2---
6. Assess exploration strategies and intrinsic motivation mechanisms in reinforcement learning.\n 6.1. Interpret the exploration–exploitation trade-off in reinforcement learning.\n 6.2. Describe intrinsic motivation and curiosity-driven learning approaches.\n1------1---
7. Evaluate engineering applications and multi-agent approaches in reinforcement learning.\n 7.1. Describe engineering applications of reinforcement learning.\n 7.2. Compare different multi-agent reinforcement learning structures.\n 7.3. Analyze an engineering problem within the reinforcement learning framework.\n32220000000
  • Info on the Institution
  • Name and Adress
  • Academic Calendar
  • Academic Authorities
  • General Description
  • List of Programmes Offered
  • General Admission Requirements
  • Recognition of Prior Learning
  • Registration Procedures
  • ECTS Credit Allocation
  • Academic Guidance
  • Info on Degree Programmes
  • PhD / Proficiency in Art
  • Master's Degree
  • Bachelor's Degree
  • Associate Degree
  • Info for Students
  • Cost of living
  • Accommodation
  • Meals
  • Medical Facilities
  • Facilities for Special Needs Students ı
  • Insurance
  • Financial Support for Students
  • Student Affairs Office
  • Info for Students
  • Learning Facilities
  • International Programmes r
  • Practical Information for Mobile Students
  • Language courses
  • Internships
  • Sports and Leisure Facilities
  • Student Associations