Completed
Our Queue Approach Can Sometimes Evaluate Algorithms that Use Deterministic Policies for Many More Time Steps than Rejection
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Towards Fast Autonomous Learners: Advances in Reinforcement Learning - 2015
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Markov Decision Process (MDP)
- 3 Reinforcement Learning
- 4 Unbiased Policy Evaluation for General RL in Short Horizons
- 5 Queue-based Offline Evaluation of Online Bandit Algorithms
- 6 Our Queue Approach Can Sometimes Evaluate Algorithms that Use Deterministic Policies for Many More Time Steps than Rejection
- 7 Sample Complexity of RL
- 8 Provably More Efficient Learners
- 9 Fast, Better Policy Search using Bayesian Optimization
- 10 Black Box Optimization
- 11 Opening the Box: Leverage Offline Policy Evaluation
- 12 Personalization & Transfer Learning for Sequential Decision Making Tasks
- 13 Latent Variable Modeling Background
- 14 Diameter Assumption: Needed for Sample Complexity Improvement in Transfer?
- 15 Active Set is Models Compatible with Current Task's Data
- 16 More Data Efficient Learning In Domains Where It Matters
