Skip to content
CampusPrep
AD-802 (B) · Reinforcement Learning/Official Syllabus

Reinforcement Learning (AD-802 (B)) - Official Syllabus

1
Unit 1

Introduction to reinforcement learning (RL)

  • Defining RL Framework and Markov Decision Process
  • Polices
  • Value Functions and Bellman Equations
  • Explorations
  • Exploitation
  • Inside an RL agent
  • Problems with reinforcement learning
2
Unit 2

Bandit algorithms

  • Bandit algorithms UCB
  • PAC
  • Median Elimination
  • Policy Gradient
  • Full RL & MDPs
  • Bellman Optimality
  • Dynamic Programming - Value iteration, Policy iteration
  • Policy Evaluation
  • Value Iteration
  • Policy Iteration
  • DP Extensions and Convergence using Contraction Mapping
  • Monte-Carlo (MC) Learning
  • Temporal-Difference (TD) Learning
  • TD-Lambda and Eligibility Traces
3
Unit 3

Q-learning & Temporal Difference Methods

  • Q-learning & Temporal Difference Methods
  • Temporal- Difference Learning
  • Eligibility Traces
  • Function Approximation
  • Least Squares Methods
  • Incremental Methods and Batch Methods
  • Deep Q-Learning analysis
  • Deep Q-Networks and Experience Replay
4
Unit 4

Fitted Q, Deep Q-Learning problems

  • Fitted Q
  • Deep Q-Learning problems
  • Advanced Q-learning algorithms
  • learning policies by imitating optimal controllers
  • DQN & Policy Gradient
  • Policy Gradient Algorithms for Full RL
  • Hierarchical RL
  • POMDPs
5
Unit 5

Actor-Critic Method

  • Actor-Critic Method
  • Inverse reinforcement learning
  • Maximum Entropy Deep Inverse Reinforcement Learning
  • Generative Adversarial Imitation Learning
  • Recent Trends in RL Architectures

Reference Books

  • Deep Learning, An MIT Press book
  • Pattern Classification
  • Reinforcement Learning: An Introduction
  • Reinforcement Learning: State-of-the-Art
Go to where you left off?

Quick Add to Notes

Save questions, your own notes and screenshots into notes filed by unit. It takes a free account.

Create free account

Have an account? Log in