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

Lecture

Policy Gradient Evaluation: Example (1-step horizon)

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 the evaluation of policy gradients using an example with a 1-step horizon, discussing the binary actor's online rule found rapidly with the log-likelihood trick and exploring various interpretations of the resulting rule. It also delves into the update rule of the example, comparing it with the Perceptron model and relating it to biology by analyzing the weight vector's direction in response to stimuli. Additionally, it explores generalization by subtracting a reward baseline and deriving an online gradient rule, showcasing its effectiveness in maximizing rewards.

Instructors (2)

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'.

Caglar Gulcehre

Official source

Related concepts (5)

Perceptron

In machine learning, the perceptron (or McCulloch-Pitts neuron) is an algorithm for supervised learning of binary classifiers. A binary classifier is a function which can decide whether or not an input, represented by a vector of numbers, belongs to some specific class. It is a type of linear classifier, i.e. a classification algorithm that makes its predictions based on a linear predictor function combining a set of weights with the feature vector.

Multilayer perceptron

A multilayer perceptron (MLP) is a misnomer for a modern feedforward artificial neural network, consisting of fully connected neurons with a nonlinear kind of activation function, organized in at least three layers, notable for being able to distinguish data that is not linearly separable. It is a misnomer because the original perceptron used a Heaviside step function, instead of a nonlinear kind of activation function (used by modern networks).

Feedforward neural network

A feedforward neural network (FNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. Its flow is uni-directional, meaning that the information in the model flows in only one direction—forward—from the input nodes, through the hidden nodes (if any) and to the output nodes, without any cycles or loops, in contrast to recurrent neural networks, which have a bi-directional flow.

Long short-term memory

Long short-term memory (LSTM) network is a recurrent neural network (RNN), aimed to deal with the vanishing gradient problem present in traditional RNNs. Its relative insensitivity to gap length is its advantage over other RNNs, hidden Markov models and other sequence learning methods. It aims to provide a short-term memory for RNN that can last thousands of timesteps, thus "long short-term memory".

Linear classifier

In the field of machine learning, the goal of statistical classification is to use an object's characteristics to identify which class (or group) it belongs to. A linear classifier achieves this by making a classification decision based on the value of a linear combination of the characteristics. An object's characteristics are also known as feature values and are typically presented to the machine in a vector called a feature vector.

Related lectures (20)

Linear Classification: Signed Distance and Perceptron

Explores signed distance, perceptron, logistic regression, cross entropy, and multi-class classification.

Introduction: classification by a simple perceptron

Covers the concept of a simple perceptron and its ability to solve linearly separable problems by imposing a separating hyperplane.

Linear Binary Classification: Perceptron, SGD, Fisher's LDA

Covers the Perceptron model, SGD, and Fisher's Linear Discriminant in binary classification.

Neural Networks: Perceptron

Covers the main concepts of neural networks, including the Perceptron model and training algorithms.

Deep Learning Paradigm