Reinforcement Learning

COURSE DURATION: 12 Weeks

@VTU COE

0.0
(0) 350 Students
Download Brochure

What you will learn

  • Software

Reinforcement learning is a paradigm that aims to model the trial-and-error learning process that is needed in many problem situations where explicit instructive signals are not available. It has roots in operations research, behavioral psychology and AI. The goal of the course is to introduce the basic mathematical foundations of reinforcement learning, as well as highlight some of the recent directions of research.

play
Introduction to RL
Preview 28:31
play
RL Framework and applications
Preview 55:06
play
Introduction to Immediate RL
Preview 24:58
play
Bandit Optimalities
Preview 17:53
play
Value function based methods
Preview 39:16

play
UCB 1
Preview 13:33
play
Concentration Bounds
Preview 24:33
play
UCB 1 Theorem
Preview 55:39
play
PAC Bounds
Preview 30:08
play
Median Elimination
Preview 40:46
play
Thompson Sampling
Preview 14:21

play
Policy Search
Preview 25:29
play
REINFORCE
Preview 41:54
play
Contextual Bandits
Preview 12:31
play
Full RL Introduction
Preview 36:49
play
Returns, Value Functions and MDPs
Preview 44:40

play
MDP Modelling
Preview 33:07
play
Bellman Equation
Preview 14:23
play
Bellman Optimality Equation
Preview 29:25
play
Cauchy Sequence and Green's Equation
Preview 31:22
play
Banach Fixed Point Theorem
Preview 25:51
play
Convergence Proof
Preview 18:03

play
Lpi Convergence
Preview 31:13
play
Value Iteration
Preview 23:27
play
Policy Iteration
Preview 13:25
play
Dynamic Programming
Preview 34:53
play
Monte Carlo
Preview 22:46
play
Control in Monte Carlo
Preview 27:39

play
Off Policy MC
Preview 16:32
play
UCT
Preview 36:23
play
TD(0)
Preview 35:10
play
TD(0) Control
Preview 22:07
play
Q-Learning
Preview 30:12
play
Afterstate
Preview 07:05

play
Eligibility Traces
Preview 46:39
play
Backward View of Eligibility Traces
Preview 32:38
play
Eligibility Trace Control
Preview 33:09
play
Thompson Sampling Recap
Preview 22:25

play
Function Approximation
Preview 38:22
play
Linear Parameterization
Preview 15:20
play
State Aggregation Methods
Preview 22:14
play
Function Approximation and Eligibility Traces
Preview 27:17
play
LSTD and LSTDQ
Preview 49:20
play
LSPI and Fitted Q
Preview 17:14

play
DQN and Fitted Q-Iteration
Preview 31:04
play
Policy Gradient Approach
Preview 36:41
play
Actor Critic and REINFORCE
Preview 12:48
play
REINFORCE (cont'd)
Preview 26:24
play
Policy Gradient with Function Approximation
Preview 20:03

play
Hierarchical Reinforcement Learning
Preview 31:26
play
Types of Optimality
Preview 22:39
play
Semi Markov Decision Processes
Preview 26:20
play
Options
Preview 22:43
play
Learning with Options
Preview 26:31
play
Hierarchical Abstract Machines
Preview 35:45

play
MAXQ
Preview 30:11
play
MAXQ Value Function Decomposition
Preview 42:03
play
Option Discovery
Preview 15:13

play
POMDP Introduction
Preview 32:27
play
Solving POMDP
Preview 43:11

play
Live Session
Preview 56:59
img
No Discussion Found

0.0

0 Reviews

5
0
4
0
3
0
2
0
1
0
Meet Your Instructor
@VTU COE
img

Instructor
3.2 Rating
2542 Students
759 Courses
About Instructor

VTU is one of the largest Technological Universities in India with 24 years of Tradition of excellence in Engineering & Technical Education, Research and Innovations. It came into existence in the year 1998 to cater the needs of Indian industries for trained technical manpower with practical experience and sound theoretical knowledge.

video

Free

  • Course Duration
    31 h 10 m 2 s
  • Course Level
    Intermediate
  • Student Enrolled
    350
  • Language
    English
This Course Includes
  • 31 h 10 m 2 s Video Lectures
  • 0 Quizzes
  • 0 Assignments
  • 0 Downloadable Resources
  • Full Lifetime Access
  • Certificate of Completion