Introduction
The Reinforcement Learning and Deep Learning (RLDL) Lab focuses on providing hands-on experience with RL and DL algorithms through practical implementations. The syllabus covers Markov Decision Processes (MDPs), Q-learning, Policy Gradient Methods, and Deep Q-Networks (DQNs). Students will learn to apply RL algorithms for decision-making in dynamic environments and use DL techniques for classification, regression, and pattern recognition. The lab emphasizes industry-relevant applications, including autonomous navigation and predictive modeling, using libraries such as TensorFlow, and PyTorch.
Course Objectives
| COB-1 | To introduce the foundation of Reinforcement learning foundation and Q Network algorithm |
| COB-2 | To understand policy optimization ,recent advanced techniques and applications of Reinforcement learning |
| COB-3 | To introduce the concept of deep learning and neural network |
| COB-4 | To understand the concept of NLP and computer vision in deep learning |
Course Outcomes
| CO | Statement | Bloom’s Level |
| ML-409P.1 | Learn how to define RL tasks and the core principals behind the RL, including policies, value functions, deriving Bellman equations and understand and work with approximate solution (deep Q Network based algorithms) | Remember
Understand |
| ML-409P.2 | Learn the policy gradient methods from vanilla to more complex cases and learn application and advanced techniques in Reinforcement Learning. | Understand
Analyze |
| ML-409P.3 | Apply neural networks and create different models for problem solving. | Apply
Create |
| ML-409P.4 | Able to Analyze images and evaluate the applications of NLP in deep learning. | Analyze
Evaluate |
CO-PO-PSO Mapping
| CO | PO1 | PO2 | PO3 | PO4 | PO5 | PO6 | PO7 | PO8 | PO9 | PO10 | PO11 | PSO1 | PSO2 |
| ML-409P.1 | 3 | 3 | 2 | 2 | 3 | – | – | 1 | 1 | – | 2 | – | – |
| ML-409P.2 | 3 | 3 | 3 | 2 | 3 | – | – | 1 | 1 | – | 3 | – | – |
| ML-409P.3 | 3 | 2 | 3 | 2 | 3 | – | – | 1 | 1 | – | 3 | – | – |
| ML-409P.4 | 3 | 3 | 2 | 3 | 3 | 1 | – | 1 | 2 | – | 3 | – | – |
Facilities
| Operating System /Software | ||
| Sr. No. | Name | Version |
| 1. | Windows | 10 PRO |
| 2. | Anaconda Navigator (Open Source) | 2.7.1 |
| Hardware | |||
| Sr. No. | Equipment Name | Specification | Quantity |
| 1. | Computer | Intel(R) Core(TM) i5-10210U CPU @ 1.60GHz 2.10 GHz with GPU | 20 |
| 2. | Printer | HP LASER Jet 1020 PLUS | 01 |
Staff
- Lab In-charge: Mihika
- Other Faculty Members: Nil
- Lab Assistant: Deepa