Safe and Efficient Exploration in Reinforcement Learning
Offered By: Fields Institute via YouTube
Course Description
Overview
Syllabus
Intro
RL beyond simulated environments?
Tuning the Swiss Free Electron Laser [with Kirschner, Muty, Hiller, Ischebeck et al.]
Challenge: Safety Constraints
Safe optimization
Safe Bayesian optimization
Illustration of Gaussian Process Inference [cf, Rasmussen & Williams 2006]
Plausible maximizers
Certifying Safety
Confidence intervals for GPS?
Online tuning of 24 parameters
Shortcomings of Safe Opt
Safe learning for dynamical systems Koller, Berkenkamp, Turchetta, K CDC 18, 19
Stylized task
Planning with confidence bounds Koller, Berkenkamp, Turchetta, K CDC 18, 19
Forwards-propagating uncertain, nonlinear dynamics
Challenges with long-term action dependencies
Safe learning-based MPC
Experimental illustration
Scaling up: Efficient Optimistic Exploration in Deep Model based Reinforcement Learning
Optimism in Model-based Deep RL
Deep Model-based RL with Confidence: H-UCRL [Curi, Berkenkamp, K, Neurips 20]
Illustration on Inverted Pendulum
Deep RL: Mujoco Half-Cheetah
Action penalty effect
What about safety?
Safety-Gym Benchmark Suite
Which priors to choose? → PAC-Bayesian Meta Learning [Rothfuss, Fortuin, Josifoski, K, ICML 2021]
Experiments - Predictive accuracy (Regression)
Meta-Learned Priors for Bayesian Optimization
Meta-Learned Priors for Sequential Decision Making
Safe and efficient exploration in real-world RL
Acknowledgments
Taught by
Fields Institute
Related Courses
Computational NeuroscienceUniversity of Washington via Coursera Reinforcement Learning
Brown University via Udacity Reinforcement Learning
Indian Institute of Technology Madras via Swayam FA17: Machine Learning
Georgia Institute of Technology via edX Introduction to Reinforcement Learning
Higher School of Economics via Coursera