Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Neural Networks for Action Learning: Brain Implementation Insights

In course

CS-456: Deep reinforcement learning

This course provides an overview and introduces modern methods for reinforcement learning (RL.) The course starts with the fundamentals of RL, such as Q-learning, and delves into commonly used approaches, like PPO and DQN. The course will introduce student ...

Description

This lecture covers neural networks for action learning, focusing on the brain's implementation of reinforcement learning algorithms. It discusses the Actor-Critic model, three-factor rules in the brain, animal conditioning experiments, and the role of dopamine as a third factor in synaptic changes.

Instructors (2)

Caglar Gulcehre

Wulfram Gerstner

Wulfram Gerstner is Director of the Laboratory of Computational Neuroscience LCN at the EPFL. His research in computational neuroscience concentrates on models of spiking neurons and spike-timing dependent plasticity, on the problem of neuronal coding in single neurons and populations, as well as on the link between biologically plausible learning rules and behavioral manifestations of learning. He teaches courses for Physicists, Computer Scientists, Mathematicians, and Life Scientists at the EPFL. After studies of Physics in Tübingen and at the Ludwig-Maximilians-University Munich (Master 1989), Wulfram Gerstner spent a year as a visiting researcher in Berkeley. He received his PhD in theoretical physics from the Technical University Munich in 1993 with a thesis on associative memory and dynamics in networks of spiking neurons. After short postdoctoral stays at Brandeis University and the Technical University of Munich, he joined the EPFL in 1996 as assistant professor. Promoted to Associate Professor with tenure in February 2001, he is since August 2006 a full professor with double appointment in the School of Computer and Communication Sciences and the School of Life Sciences. Wulfram Gerstner has been invited speaker at numerous international conferences and workshops. He has served on the editorial board of the Journal of Neuroscience, Network: Computation in Neural Systems', Journal of Computational Neuroscience', and `Science'.

Official source

Related concepts (29)

Reinforcement learning

Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. Reinforcement learning differs from supervised learning in not needing labelled input/output pairs to be presented, and in not needing sub-optimal actions to be explicitly corrected.

Deep reinforcement learning

Deep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs (e.g.

Q-learning

Q-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. It does not require a model of the environment (hence "model-free"), and it can handle problems with stochastic transitions and rewards without requiring adaptations. For any finite Markov decision process (FMDP), Q-learning finds an optimal policy in the sense of maximizing the expected value of the total reward over any and all successive steps, starting from the current state.

Classical conditioning

Classical conditioning (also respondent conditioning and Pavlovian conditioning) is a behavioral procedure in which a biologically potent physiological stimulus (e.g. food) is paired with a neutral stimulus (e.g. the sound of a musical triangle). The term classical conditioning refers to the process of an automatic, conditioned response that is paired with a specific stimulus. The Russian physiologist Ivan Pavlov studied classical conditioning with detailed experiments with dogs, and published the experimental results in 1897.

Operant conditioning

Operant conditioning, also called instrumental conditioning, is a learning process where behaviors are modified through the association of stimuli with reinforcement or punishment. In it, operants—behaviors that affect one's environment—are conditioned to occur or not occur depending on the environmental consequences of the behavior. Operant conditioning originated in the work of Edward Thorndike, whose law of effect theorised that behaviors arise as a result of whether their consequences are satisfying or discomforting.

Related lectures (35)

Neural Networks for Action Learning: Three-Factor Rules and Dopamine

Explores neural networks learning by reward, actor-critic structures, synaptic plasticity, and the role of dopamine in synaptic changes.

Reinforcement Learning: Reward-based Learning

Explores artificial neural networks, reward information in the brain, animal conditioning, deep reinforcement learning, and a quiz on rewards.

Perception: Data-Driven Approaches

Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.

Neural Networks: Multilayer Learning

Covers the fundamentals of multilayer neural networks and deep learning, including back-propagation and network architectures like LeNet, AlexNet, and VGG-16.

The Hidden Convex Optimization Landscape of Deep Neural Networks