Natasha Jaques - Social Reinforcement Learning - IPAM at UCLA

Natasha Jaques - Social Reinforcement Learning - IPAM at UCLA

Institute for Pure & Applied Mathematics (IPAM) via YouTube Direct link

Social Learning with Multi-Agent RL

11 of 12

11 of 12

Social Learning with Multi-Agent RL

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Natasha Jaques - Social Reinforcement Learning - IPAM at UCLA

Automatically move to the next video in the Classroom when playback concludes

  1. 1 What abilities does an Al assistant need?
  2. 2 Social learning -Learning from other intelligent agents in your environment
  3. 3 Generalization and transfer in RL
  4. 4 Adversarial environment generation
  5. 5 Is there a more elegant way to ensure the adversary does not create impossible environments?
  6. 6 PAIRED (Protagonist Antagonist Induced Regret Environment Design) • Constrain the adversary using the performance of a second agent in the same environment
  7. 7 Environment Generation for Web Navigation
  8. 8 Web navigation - task success
  9. 9 Conclusions
  10. 10 Outline
  11. 11 Social Learning with Multi-Agent RL
  12. 12 Agents are able to use social learning

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.