Multi Agent Deep Reinforcement Learning for Autonomous Driving

Core concept of reinforcement learning.
A centralised controller receives the state from the environment and outputs the actions for all agents.
python src/main.py --config=qmix --env-config=macad 

--

--

--

Wandering in the world of artificial intelligence and blockchain

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Proof that The Beatles Were Ahead of Their Time: An Exploration of American Pop Music History with…

From Seq2Seq to BERT

Image Caption Generator using ResNet50 and LSTM model

Fine Tuning TensorFlow Bert Model for Sentiment Analysis

Deep RL: a Model-Based approach (part 3)

A Self-supervised Learning Framework for Discovery

Azure Cognitive Search + Azure Cognitive Services — a marriage made in heaven

Natural Language Processing- A Go through basic functions

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Kai Jun Eer

Kai Jun Eer

Wandering in the world of artificial intelligence and blockchain

More from Medium

Training a Reinforcement Learning agent to fish in Stardew Valley

Sokoban Game for Reinforcement Learning

Implementing multi-armed bandits in reinforcement learning

Generative Adversarial Network (GAN) for Creating Synthetic EEG/LFP Both Normal and Abnormal