liveBook · Manning

Deep learning

As explained in Applied Reinforcement Learning

Deep learning is a machine-learning approach that learns hierarchical representations and predictions using neural networks with multiple learned layers.

Deep learning extends function approximation: a neural network maps high-dimensional inputs to predictions while learning useful representations instead of relying on hand-designed features. In deep Q-learning, this provides a way to estimate values from complex states. section 8.2

Each layer applies a weighted sum and bias, followed by a nonlinear activation such as ReLU. Without nonlinearity, stacked layers reduce to one linear transformation. Deep reinforcement learning commonly uses ReLU in hidden layers and linear outputs for Q-values. section 8.2

Figure 8.4 End-to-end learning in deep neural networks

Trace the end-to-end learning loop from input through prediction and parameter updates. section 8.2

Figure 8.5 The building block of deep networks: neurons and activation functions

See how a neuron combines inputs and how activation functions add nonlinearity. section 8.2

How Applied Reinforcement Learning covers it

How deep it goes
Explains the forward pass, layer transformations, neuron computation, and activation role.
Examples
Names images, sensor vectors, medical records, and high-dimensional states as possible network inputs.
What it assumes
Builds on value-function approximation and temporal-difference error while introducing learned representations and network layers.
What you can do after
Understand how learned layers and nonlinear activations transform complex inputs into Q-value predictions.
How it connects
Connects function approximation and temporal-difference error with neural networks, reinforcement learning, ReLU, and Q-values.

Also explained in

Compare how 20 books explain deep learning →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Applied Reinforcement Learning. The section links point to the parts of the book it draws on.