Search
John Schulman by talkRL | Mixes.VuiZ.Net
John Schulman
By
talkRL
Tags:
#Reinforcement learning
#Machine learning
#Artificial intelligence
John Schulman
talkRL
0:00
0:00
Description
John Schulman, OpenAI cofounder and researcher, inventor of PPO/TRPO talks RL from human feedback, tuning GPT-3 to follow instructions (InstructGPT) and answer long-form questions using the internet (WebGPT), AI alignment, AGI timelines, and more!
Direct Download
More from
talkRL
Thomas Frost on Clinical RL with Natural Timings
talkRL
2mo ago
87:23
0
#Reinforcement learning
#Machine learning
#Artificial intelligence
David Abel on the Science of Agency @ RLDM 2025
talkRL
1y ago
59:41
0
#Reinforcement learning
#Machine learning
#Artificial intelligence
Thomas Akam on Model-based RL in the Brain
talkRL
1y ago
52:05
0
#Reinforcement learning
#Machine learning
#Artificial intelligence
Stefano Albrecht on Multi-Agent RL @ RLDM 2025
talkRL
1y ago
31:33
0
#Reinforcement learning
#Machine learning
#Artificial intelligence
Abhishek Naik on Continuing RL & Average Reward
talkRL
1y ago
81:39
0
#Reinforcement learning
#Machine learning
#Artificial intelligence
