Implementation of differential game theoretic solution for a simple spatial negotiation problem between two agents.

ILQR controller acting on a two link arm model of the human arm to demonstrate reaching between points in a 2d plane

Implementation of an assist-as-needed controller in the joint space of gait based on deviations of the ankle.

Reinforcement learning of point to point reaching

Solutions and figures for problems from Reinforcement Learning: An Introduction Sutton&Barto

(Prioritized experience replay, random uniform replay) with tabular-Q for blind cliffwalk problem introduced as a motivating example in the publication Schaul et al., 2015

Sum tree data structure for stochastic priority sampling

Identifying actions belonging to the Uncontrolled Manifold for bimanual manipulation of a cursor using reinforcement learning.

Simulating gamblers ruin in a game of roulette using random walks.