RTMNU Final Computer Engg syllabus

RTMNU · Final Year B.Tech Computer Engineering · CBCS

Reinforcement Learning

BTCME801.2T · Elective VI · Semester VIII · 3 credits · College 30 + university 70

One of the Elective VI options. An NPTEL course: its page lists twelve weeks, grouped here into five units.

All notes for this subject
  1. Unit 1: Introduction and Bandit Algorithms (weeks 1–3)

    The trial-and-error learning problem and its roots; bandit algorithms — UCB, PAC algorithms and median elimination, and policy-gradient bandits.

    Examined in the 70-mark end-semester paper

    • Reinforcement learning: elements and scope
    • Multi-armed bandits
    • Action selection: optimistic values, UCB and gradient bandits
    • PAC bandit algorithms and median elimination
  2. Unit 2: Full Reinforcement Learning and MDPs (weeks 4–5)

    The full reinforcement-learning problem as a Markov decision process, value functions and Bellman optimality.

    Examined in the 70-mark end-semester paper

    • Finite Markov decision processes
    • Policies, value functions and optimality
  3. Unit 3: Dynamic Programming, TD Methods and Eligibility Traces (weeks 6–7)

    Dynamic-programming solutions of MDPs, temporal-difference methods, and eligibility traces.

    Examined in the 70-mark end-semester paper

    • Policy evaluation and policy iteration
    • Value iteration and generalised policy iteration
    • Temporal-difference prediction
    • Sarsa and Q-learning
    • Eligibility traces and TD(λ)
  4. Unit 4: Function Approximation and Deep RL (weeks 8–10)

    Function approximation and least-squares methods; fitted Q-iteration, deep Q-networks and policy gradients for full RL.

    Examined in the 70-mark end-semester paper

    • Value-function approximation
    • Semi-gradient methods and linear function approximation
    • Deep Q-networks
    • Policy gradient theorem
  5. Unit 5: Hierarchical RL and POMDPs (weeks 11–12)

    Hierarchical reinforcement learning and partially observable Markov decision processes.

    Examined in the 70-mark end-semester paper

    • Hierarchical reinforcement learning
    • Partially observable MDPs

Unit contents are summarised from the official RTMNU syllabus . AiCanCode.org is not affiliated with Rashtrasant Tukadoji Maharaj Nagpur University (RTMNU).