Completed
Intro
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Alternatives to Reinforcement Learning for Real-World Problems
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 LET'S TALK ABOUT REINFORCEMENT LEARNING
- 3 THE THREE MACHINE LEARNS
- 4 EMBODIED LEARNING
- 5 AGENT-BASED LEARNING
- 6 THE DECISION POLICY
- 7 THE REWARD
- 8 TWO IDEAS
- 9 DEALING WITH UNCERTAINTY
- 10 REQUIREMENTS OF BIG SUCCESSES
- 11 SIMULATION
- 12 FULLY OBSERVABLE
- 13 TRANSFERABILITY OF METHOD
- 14 WHAT IS THE COST OF AN ERROR?
- 15 CAN WE APPLY THIS TO REAL PROBLEMS?
- 16 REAL-WORLD ALTERNATIVES
- 17 WHAT ARE WE TRYING TO SOLVE
- 18 TOOLS
- 19 MICROSOFT AZURE
- 20 AWS SAGEMAKER
- 21 WHEN SHOULD I USE CONTEXTUAL BANDITS?
- 22 LIMITATIONS
- 23 BEHAVIORAL CLONING
- 24 EXPERT SYSTEMS SUPERVISED LEARNING
- 25 COLLECT TRAJECTORIES FROM AN EXPERT
- 26 BREAK UP INTO STATE / ACTION PAIRS
- 27 TRAIN A MODEL ON THE TRAJECTORIES
- 28 INTERACTIVE EXPERTS
- 29 APPLICATIONS
- 30 WHEN SHOULD I USE IMITATION LEARNING?
- 31 SCALABILITY CONCERNS
- 32 CAPTURING DATASETS
- 33 IMITATION LEARNING + REINFORCEMENT LEARNING
- 34 RESOURCES
- 35 OFFLINE RL
- 36 WHY IS THIS EXCITING?
