One thought on “Lecture 22 Sim2Real and Domain Randomization — CS287-FA19 Advanced Robotics at UC Berkeley

  1. L1 Course Introduction:
    L2 MDPs: Exact Methods:
    L3 Discretization of Continuous State Space MDPs:
    L4 Function Approximation / Feature-based Representations:
    L5 LQR, iterative LQR / Differential Dynamic Programming:
    L6 Unconstrained Optimization:
    L7 Constrained Optimization:
    L8 Optimization-based Control: Collocation, Shooting, MPC (basics/foundations):
    L9 Optimization-based Control: Collocation, Shooting, MPC, Contact-Invariant Optimization (advanced) — Igor Mordatch:
    L10 Motion Planning: RRT, PRM, Trajopt, 3-d poses:
    L11 Probability Review, Bayes Filters, Multivariate Gaussians:
    L12 Kalman Filtering, EKF, UKF — Ignasi Clavera:
    L13 Smoother, MAP, Maximum Likelihood, EM, KF parameter estimation:
    L14 Particle Filters — Wolfram Burgard:–yWn8_ds
    L15 POMDPs:
    L17 Imitation Learning — Laura Smith:
    L18 RL1: Policy Gradients:
    L19 RL2: Off-policy RL:
    L20 RL3: Model-based RL:
    L21 How do simulators work?
    L22 Sim2Real — Josh Tobin:
    L23 INDUSTRY: Skydio (drones): Adam Bry/Hayk Martirosyan:
    L24 Backstories behind how some papers were originated and came together:
    L25 Autonomous Helicopters and Course Wrap-Up:

    Full Course:

Leave a Reply

Your email address will not be published. Required fields are marked *