Kai Jappe Sandbrink's starred repositories
DLC2Kinematics
a module for kinematic analysis of deeplabcut outputs
ObserveBet
Code for Observe or Bet project (Gershman Lab, 2016)
observeorbet
Experiments, models and data for the "observe or bet" paper.
optimising-transdiagnostic-measurement
Repository for data and analysis code for transdiagnostic measurement paper
Docker4DeepLabCut2.0
Docker container for running DeepLabCut 2.0, 2.1 (linux support only). Now, DLC main supports 2.2+
Meta-RL-Harlow
PyTorch implementation of two variants of the Harlow visual fixation task (PsychLab and 1D version). Reproduces the results found in two papers. Check the ReadMe for more details!
drl-policy-gradient-cartpole
PyTorch application of reinforcement learning Policy Gradient algorithms in OpenAI Cartpole - REINFORCE, Actor-Critic, A2C, A3C
ReinforcementLearning-AtariGame
Pytorch LSTM RNN for reinforcement learning to play Atari games from OpenAI Universe. We also use Google Deep Mind's Asynchronous Advantage Actor-Critic (A3C) Algorithm. This is much superior and efficient than DQN and obsoletes it. Can play on many games
two-step-task
Implementation of the two-step-task as described in "Prefrontal cortex as a meta-reinforcement learning system" and "Learning to Reinforcement Learn".
empowerment
Repository for research done on empowerment & mutual info maximization
Maximising-Neural-Information-Processing
Maximum Mutual Information Estimation and Optimization
variational_empowerment
tensorflow implementation of https://arxiv.org/abs/1509.08731
DeepLabCut
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans
scikit-kinematics
Python functions for working with 3D kinematics.