AI Simulator


2022-08-14 11:40:45 +0000 - paradite

Deep Q-networks (DQN) is a type of deep reinforcement learning algorithm developed by DeepMind in 2013.

DQN uses a deep convolutional neural network to approximate the Q-value of action in a given state.

Hyperparameters

There are several hyperparameters that can be tuned to get better results with DQN.

Performance metrics

We can use the Q value and loss as two metrics to evaluate the performance of a DQN model:

Q value

Loss

Examples

DQN can be trained to play many single-player games, for example Tetris, Snake, 2048.

This is a screenshot of tfboard for training DQN to play 2048 over 100M frames:

Observations on key metrics:

This is a screenshot of tfboard for training DQN to play AI Simulator: Robot over 13M frames:

Observations on key metrics:

Further readings

DQN paper

Interactive demos