Skip to content
dr.Pep
dr.Pep
knows better
  • Single Sentence Summaries
  • Linux
  • Analytics
  • Recent posts
Copyright © 2022 Pepijn van der Laan.
All rights reserved.
Determining the value function is a difficult problem that is nonetheless key to safely and effectively using reinforcement learning

Determining the value function is a difficult problem that is nonetheless key to safely and effectively using reinforcement learning

Brian Christian – The Alignment Problem

The analogies between human and machine learning strategies are skillfully narrated, but rather drawn out.

Tags
AI (10) Analytics (5) Art (8) Artificial Intelligence (4) Biology (5) Brain science (5) Change (5) Chemistry (4) Classics (4) Collaboration (5) Culture (39) Data science (8) Design (6) Economics (20) Economy (6) Entrepreneurship (15) Ethics (10) Evolution (7) Hacking (6) Health (4) History (58) Innovation (58) Investing (5) IT (7) Journalism (5) Leadership (25) Linux (8) Literature (4) Marketing (10) Mathematics (6) Personal development (4) Philosophy (12) Physics (8) Politics (46) Psychology (8) Retail (5) Science (30) Sociology (7) Start-ups (4) Startup (10) Statistics (13) Strategy (7) Technology (42) Ubuntu 20 (8) USA (28)
Archives
Copyright © 2022 Pepijn van der Laan.
All rights reserved.