2019 Air Street Capital The State of AI Report 2019 · page 17 of 136
The slide uses technical diagrams to illustrate RL concepts like memory-based exploration and skill-based discriminator training.
Consulting deck · industry_trends · present_framework · dense density
Slide locked Sign in to view
Slide schematic 6/7
callout 0/1 image 2/2 paragraph 2/2 title 2/2
1 without position callout 1
callout
Components 7
callout illustration illustration paragraph paragraph action-title headline
Tools 2
Curiosity Gap slide · 70%
How can agents learn to solve tasks when their reward is either sparse or non-existent? Encourage curiosity.
Problem Statement Canvas slide · 60%In RL, agents learn tasks by trial and error. They must balance exploration (trying new behaviors) with exploitation (repeating behaviors that work).
Metrics 0
∅
No metrics
No metric insight is anchored to this slide.
Frameworks 1