BSDA5007 · workspace

Reinforcement Learning

Syllabus, study tools, lectures, and curriculum map.

← Back to hub

More courses

Browse course shelf

Weekly outline

Syllabus

Week topics from the course map

00W00

Topic

Incomplete

01W01

Review of ML fundamentals – Classification, Regression. Review of probability theory and optimization concepts.

Incomplete

02W02

RL Framework; Supervised learning vs. RL; Explore-Exploit Dilemma; Examples.

Incomplete

03W03

MAB: Definition, Uses, Algorithms, Contextual Bandits, Transition to full RL, Intro to full RL problem

Incomplete

04W04

Intro to MDPs: Definitions , Returns, Value function, Q-function.

Incomplete

05W05

Bellman Equation, DP, Value Iteration, Policy Iteration, Generalized Policy Iteration.

Incomplete

06W06

Evaluation and Control: TD learning, SARSA, Q-learning, Monte Carlo, TD Lambda, Eligibility Traces.

Incomplete

07W07

Maximization-Bias & Representations: Double Q learning, Tabular learning vs. Parameterized, Q-learning with NNs

Incomplete

08W08

Function approximation: Semi-gradient methods, SGD, DQNs, Replay Buffer.

Incomplete

09W09

Policy Gradients: Introduction, Motivation, REINFORCE, PG theorem, Introduction to AC methods

Incomplete

010W10

Actor-Critic Methods, Baselines, Advantage AC, A3C

Incomplete

011W11

Advanced PG/A-C methods: Deterministic PG and DDPG, Soft Actor-Critic (SAC)

Incomplete

012W12

Model-Based RL: Introduction, Motivation, Connections to Planning, Types of MBRL, Benefits, RL with a Learnt Model, Dyna-style models, Latent variable

Incomplete

Study tools

Memorize first

Compact recall strip

Open notes

5 min

Deep Q-Networks: Experience Replay, Target Networks, Rainbow

Open this first for the core logic and traps.

Dive in

5 min

Markov Decision Processes & Bellman Equations

Open this first for the core logic and traps.

Dive in

5 min

Multi-Armed Bandits: Exploration vs Exploitation

Open this first for the core logic and traps.

Dive in

Practice Dock

One drill at a time, with Theo hints, teacher lanes, and a replay queue.

Use this when the theory is already clear and the goal is fast, clean retrieval under pressure. Mark weak questions, copy a revision pack, and move on.

TheoTeacherTextbookSpeedrun

Ask less. Recall more.

Open Practice Dock

SM-2 Active

Spaced Repetition

Flashcards

Spaced repetition engine for long-term retention of core concepts.

Start session

Not Available

Interactive Simulations

Visual Labs

Exam Mode

Adaptive Practice

Mock Exam

Set paper

Code Protocol

OPPE Simulator

Secure Comm-Link Terminal

Secure Comm-Link // Playlist Connected

Uplink 12ms

Syllabus Synchronization: Active

Open current cue

Syllabus Matrix Registry

Global Course Index

Open Full Frame

Master Registry

v6.4 Directory

Foundational

Diploma

BSc Degree

BS Degree

PG / MTech

BSDA5007

PG / MTech

4 Credits

Special topics in Machine Learning (Reinforcement Learning)

To enable the student to understand the reinforcement learning paradigm, to be able to identify when an RL formulation is appropriate, to understan...

Deployment Hub External Docs

Execution Protocol

Module 0

Topic

Module 1

Review of ML fundamentals – Classification, Regression. Review of probability theory and optimization concepts.

Module 2

RL Framework; Supervised learning vs. RL; Explore-Exploit Dilemma; Examples.

Module 3

MAB: Definition, Uses, Algorithms, Contextual Bandits, Transition to full RL, Intro to full RL problem

Module 4

Intro to MDPs: Definitions , Returns, Value function, Q-function.

Module 5

Bellman Equation, DP, Value Iteration, Policy Iteration, Generalized Policy Iteration.

Module 6

Evaluation and Control: TD learning, SARSA, Q-learning, Monte Carlo, TD Lambda, Eligibility Traces.

Module 7

Maximization-Bias & Representations: Double Q learning, Tabular learning vs. Parameterized, Q-learning with NNs

Module 8

Function approximation: Semi-gradient methods, SGD, DQNs, Replay Buffer.

Module 9

Policy Gradients: Introduction, Motivation, REINFORCE, PG theorem, Introduction to AC methods

Module 10

Actor-Critic Methods, Baselines, Advantage AC, A3C

Module 11

Advanced PG/A-C methods: Deterministic PG and DDPG, Soft Actor-Critic (SAC)

Module 12

Syllabus

Topic

Review of ML fundamentals – Classification, Regression. Review of probability theory and optimization concepts.

RL Framework; Supervised learning vs. RL; Explore-Exploit Dilemma; Examples.

MAB: Definition, Uses, Algorithms, Contextual Bandits, Transition to full RL, Intro to full RL problem

Intro to MDPs: Definitions , Returns, Value function, Q-function.

Bellman Equation, DP, Value Iteration, Policy Iteration, Generalized Policy Iteration.

Evaluation and Control: TD learning, SARSA, Q-learning, Monte Carlo, TD Lambda, Eligibility Traces.

Maximization-Bias & Representations: Double Q learning, Tabular learning vs. Parameterized, Q-learning with NNs

Function approximation: Semi-gradient methods, SGD, DQNs, Replay Buffer.

Policy Gradients: Introduction, Motivation, REINFORCE, PG theorem, Introduction to AC methods

Actor-Critic Methods, Baselines, Advantage AC, A3C

Advanced PG/A-C methods: Deterministic PG and DDPG, Soft Actor-Critic (SAC)

Model-Based RL: Introduction, Motivation, Connections to Planning, Types of MBRL, Benefits, RL with a Learnt Model, Dyna-style models, Latent variable

Compact recall strip

One drill at a time, with Theo hints, teacher lanes, and a replay queue.

Flashcards

Visual Labs

Mock Exam

OPPE Simulator

Secure Comm-Link Terminal

Syllabus Matrix Registry

Master Registry

Foundational

Diploma

BSc Degree

BS Degree

PG / MTech

Special topics in Machine Learning (Reinforcement Learning)

Execution Protocol

Topic

Review of ML fundamentals – Classification, Regression. Review of probability theory and optimization concepts.

RL Framework; Supervised learning vs. RL; Explore-Exploit Dilemma; Examples.

MAB: Definition, Uses, Algorithms, Contextual Bandits, Transition to full RL, Intro to full RL problem

Intro to MDPs: Definitions , Returns, Value function, Q-function.

Bellman Equation, DP, Value Iteration, Policy Iteration, Generalized Policy Iteration.

Evaluation and Control: TD learning, SARSA, Q-learning, Monte Carlo, TD Lambda, Eligibility Traces.

Maximization-Bias & Representations: Double Q learning, Tabular learning vs. Parameterized, Q-learning with NNs

Function approximation: Semi-gradient methods, SGD, DQNs, Replay Buffer.

Policy Gradients: Introduction, Motivation, REINFORCE, PG theorem, Introduction to AC methods

Actor-Critic Methods, Baselines, Advantage AC, A3C

Advanced PG/A-C methods: Deterministic PG and DDPG, Soft Actor-Critic (SAC)

Model-Based RL: Introduction, Motivation, Connections to Planning, Types of MBRL, Benefits, RL with a Learnt Model, Dyna-style models, Latent variable

Intelligence Hub