Video Lectures of Wulfram Gerstner:
Reinforcement Learning
Part A covers classical methods of Reinforcement Learning whereas Part B covers modern topics such as deep reinforcment learning, intrinsic motivation and reward-based learning in the brain.
A: Foundations of Reinforcement Learning
This part A covers classical methods of Reinforcement Learning.
B: Deep Reinforcement Learning, Applications, Intrinsic Rewards, and the Brain
This part B covers modern methods of 'Deep Reinforcement Learning' with applications to games, robotics, intrinsically motivated agents, and the brain.
- Deep Reinforcement Learning Lecture 1.
Applications in Video Games and Simulated Robotics (53 min, lectured by Johanni Brea)
Part 1 (Lecture recording 2024)
Model-free Deep Reinforcement Learning for Video Games: DQN, A2C and Importance Sampling (Lecture recording starts at timer 6:30)
Part 2 (Lecture recording 2024)
Unfortunately only the sound track was recorded but not the lecture slides. Please look Version from 2023
Part 1 (version 2023)-
Mini-Batches in On- and Off-Policy Deep Reinforcement Learning
(18 min)
Part 2 (version 2023) -
Proximal Policy Optimization for Continuous Control
(25 min)
Part 3 (version 2023) -
Deep Deterministic Policy Gradient for Continuous Control
(10 min)
- Deep Reinforcement Learning Lecture 2.
Applications of Model-Based RL in Board Games (Chess, Go, others) (55 min, lectured by Johanni Brea)
Part 1 (Lecture recording 2024)
Basics of Model-Based Deep RL and Variational State Tabulation.
(video starts at Min 0:40, Model-based RL starts at Min 14:00. Unfortunately, the sound track stops after 34 minutes, please refer to version from 2023)
Part 2 (Lecture recording 2024)
alpha-zero,mu-zero, agent 57,
Part 1 (Version 2023) -
Background Planning and Variational State Tabulation
(16 min)
Part 2 (Version 2023) -
Monte Carlo Tree Search and Alpha Zero
(25 min)
Part 3 (Version 2023) -
MuZero
(14 min)
slides for Deep Reinforcement Learning - Lectures 1+ 2: Deep Reinforcement Learning
- Reinforcement Learning and AI: Ethics and Regulation
Lecture recording 2024
The need of regulation
- Large Language Models and Reinforcement Learning (C. Gulcehre)
Lecture recording 2024
Human-AI alignment
- Reinforcement Learning and the Brain: 3-factor rules and brain-style computing (67 min)
Part 1 -
Introduction: Roots of Reinforcement Learning in Brain Science
(10 min)
Part 2 -
Coarse Brain Anatomy and Reinforcement Learning
(8 min)
Part 3 -
Synaptic Plasticity and 'Learning rules'
(17 min)
Part 4 -
What Learning Rules to expect for Reinforcement Learning?
(4 min)
Part 5 -
Three-factor Learning Rules
(14 min)
Part 6 -
Policy Gradient with eligibility traces revisited
(5 min)
Part 7 -
Dopamine as a third factor is a TD-like signal
(9 min)
slides for Reinforcement Learning and the Brain: 3-factor rules
- Intrinsically motivated agents 1: Exploration, Novelty, and Surprise in Reinforcement Learning (54 min)
Part 1 -
Introduction: Novelty is not Surprise
(10 min)
Part 2 -
Why is Surprise Useful?
(6 min)
Part 3 -
Change Point Detection with the Bayes-Factor Surprise
(7 min)
Part 4 -
Why is Novelty Useful?
(14 min)
Part 5 -
A Hybrid Model with Surprise, Novelty, and Reward
(3 min)
Part 6 -
Exploration of a Markov environment by Humans and Artificial Agents
(14 min)
slides for Exploration, Novelty, and Surprise in Reinforcement Learning
- Intrinsically motivated Agents 2: Curiosity-Driven Exploration in Reinforcement Learning (71 min, lectured by Alireza Modirshanechi)
Part 1 -
Exploration Bonus in Tabular Reinforcement Learning (23 min)
Part 2 -
Curiosity-driven Reinforcement Learning (48 min)
- Intrinsically motivated agents 3: Noisy-TV problem and search strategies in human and artificial agents (45 min, lectured by Alireza Modirshanechi)
All parts -
Noisy-TV Problem and Drawbacks of Curiosity-driven Reinforcement Learning
Recommended Textbook
Reinforcement Learning: an Introduction
by R. Sutton and A. Barto (MIT Press)
|