Software from RLLAB

Deep Learning

  • Introduction to TensorFlow
  • Multilayer perceptrons (MLP)
  • Convolutional neural networks (CNN)
  • Recurrent neural networks (RNN)

Reinforcement Learning

  • Behavior Cloning (Supervised Learning)
  • Value Iteration and Policy Iteration
  • SARSA and Q Learning
  • Deep Q Learning
  • Policy Gradient
  • Actor Critic Methods
  • Model based RL and Learning from Demonstrations
  • Inverse Reinforcement Learning

Autonomous Driving

Robotics and Computer Vision

  • Jaegoo Choy, Geonho Cha, and Songhwai Oh, "Unsupervised 3D Link Segmentation of Articulated Objects with a
    Mixture of Coherent Point Drift," IEEE Robotics and Automation Letters, May. 2022.

More Software

A neural network for generative adversarial synthesis from language to action. The algorithm is based on the following paper:

A detection algorithm for frequently and heavily overlapped pedestrians. This algorithm is based on the following paper:

A variant of random forest algorithm using compressive sensing which is applied to estimate head pose from a low resolution image. This algorithm is based on the following paper:

A low-rank matrix approximation algorithm using elastic-net regularization of singular values. This algorithm is based on the following papers:

A multi-target tracking algorithm for tracking an unknown number of targets in a cluttered environment. This algorithm is based on the following article: