Training Agentic Reasoners - Reinforcement Learning for Multi-Turn Tool Calling

Training Agentic Reasoners - Reinforcement Learning for Multi-Turn Tool Calling

AI Engineer via YouTube Direct link

[00:00] Introduction to the idea that reasoning and agents are similar.

1 of 8

1 of 8

[00:00] Introduction to the idea that reasoning and agents are similar.

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Training Agentic Reasoners - Reinforcement Learning for Multi-Turn Tool Calling

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

  1. 1 [00:00] Introduction to the idea that reasoning and agents are similar.
  2. 2 [01:05] The growing effectiveness of Reinforcement Learning RL in AI.
  3. 3 [03:04] The complexities and challenges of implementing RL.
  4. 4 [04:41] The connection between popular AI products agents and RL fine-tuning.
  5. 5 [07:18] The core process of Reinforcement Learning.
  6. 6 [10:21] The importance of tools and real-world tasks for agents.
  7. 7 [12:13] The problem of "reward hacking" and how to design better evaluations.
  8. 8 [14:51] Future directions for agentic systems and a practical toolkit for implementation.

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.