liveBook · Manning

DQN

As explained in Evolutionary Deep Learning: Genetic algorithms and neural networks

Deep Q-learning is reinforcement learning that uses a deep neural network to approximate action-value estimates instead of storing them only in a Q-table.

DQN applies deep learning to reinforcement learning by replacing a Q-table with a neural network that estimates action values. The Q-learning equation supplies the training target, so the network learns through a supervised-training process while acting in an environment. section 11.2 section 11.6

Lunar Lander

A DQN agent can be trained on Gym’s LunarLander environment by configuring batch size and episode count, reshaping observations, selecting actions, storing transitions, and replaying batches. Training results can be inspected through reward, exploration-rate, memory-usage, and loss plots. section 11.5

How Evolutionary Deep Learning: Genetic algorithms and neural networks covers it

How deep it goes
Explains the Q-learning target, network architecture, exploration, replay, and training loop, but does not derive the method mathematically.
Examples
Uses CartPole, Acrobot, MountainCar, LunarLander, Atari games, Gym notebooks, training plots, and replay-code exercises.
What it assumes
Assumes reinforcement-learning and Q-learning basics plus state/action spaces, while distinguishing reinforcement, supervised, and generative learning.
What you can do after
Build it from scratch in Keras, train it on Gym environments, inspect rewards and losses, and experiment with environments and hyperparameters.
How it connects
Connects reinforcement learning, Q-learning, deep learning, experience replay, OpenAI Gym, and supervised training.
Cover of Evolutionary Deep Learning: Genetic algorithms and neural networks
liveBookmanning.com
Read Evolutionary Deep Learning: Genetic algorithms and neural networks on liveBook Get the book at manning.com

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Evolutionary Deep Learning: Genetic algorithms and neural networks. The section links point to the parts of the book it draws on.