Venue: Kresit classroom SIC 201
Lectures Completed
Host: Harshad Khadilkar
harshadk@iitb.ac.in
Office: New CSE Bldg, 207
Sign-up sheet: Click here
Consolidated summary of Deep RL Workshop lectures -- Download: Document
Basics of RL, connection to control theory, tabular RL, simple DQN -- Download: Documents, Video recording
Target networks, Prioritised replay, Hindsight replay, Rainbow, Directed exploration -- Download: Documents, Video recording
Policy gradients, REINFORCE, A2C, A3C, DDPG, SAC -- Download: Documents, Video recording
Model based Deep RL, Dream to Control, Alpha Go, Modern chess engines (guest talk) -- Download: Documents, Video recording
RL as sequence prediction, RL for static optimisation, Multi-Agent RL, Reward shaping -- Download: Documents, Video recording