Media Summary: Watch science advance live! I am an MIT PhD and stream my research on reinforcement learning. You can also find me here: ... Dive into 10 levels of the RL stack with Joseph Suarez, a newly minted MIT PhD and the creator of Neural MMO + The teams shipping production AI today are figuring it out in real time. ​On July 23, we're bringing them together in London to ...

Pufferlib Rlc 2025 Outstanding Paper - Detailed Analysis & Overview

Watch science advance live! I am an MIT PhD and stream my research on reinforcement learning. You can also find me here: ... Dive into 10 levels of the RL stack with Joseph Suarez, a newly minted MIT PhD and the creator of Neural MMO + The teams shipping production AI today are figuring it out in real time. ​On July 23, we're bringing them together in London to ... Project Website: Songyuan Zhang's talk at Robotics: Science and Systems Dr. Joseph Suarez, creator of Neural MMO, presents

Photo Gallery

PufferLib RLC 2025 Outstanding Paper: RL at Millions of Steps per Second
PufferLib 3.0: Fast and Sane Reinforcement Learning
PufferLib - New frontiers in RL
Live Dev - PufferLib is Fixing Reinforcement Learning
PufferLib - New frontiers in RL
PufferLib - New frontiers in RL
Live Dev - PufferLib is Fixing Reinforcement Learning
How Speeding Up RL Led to Pufferlib (4.8K Stars) |  with Joseph Suarez
The Full Reinforcement Learning Iceberg
TSAI Conf London
RSS 2025 Talk on Def-MARL (Best Student Paper Award)
PufferLib 1.0 - Making Reinforcement Learning Play Nice
View Detailed Profile
PufferLib RLC 2025 Outstanding Paper: RL at Millions of Steps per Second

PufferLib RLC 2025 Outstanding Paper: RL at Millions of Steps per Second

RLC 2025

PufferLib 3.0: Fast and Sane Reinforcement Learning

PufferLib 3.0: Fast and Sane Reinforcement Learning

PufferLib

PufferLib - New frontiers in RL

PufferLib - New frontiers in RL

Watch science advance live! I am an MIT PhD and stream my research on reinforcement learning. You can also find me here: ...

Live Dev - PufferLib is Fixing Reinforcement Learning

Live Dev - PufferLib is Fixing Reinforcement Learning

Follow jsuarez5341 on X Star https://github.com/pufferai/

PufferLib - New frontiers in RL

PufferLib - New frontiers in RL

Watch science advance live! I am an MIT PhD and stream my research on reinforcement learning. You can also find me here: ...

PufferLib - New frontiers in RL

PufferLib - New frontiers in RL

Watch science advance live! I am an MIT PhD and stream my research on reinforcement learning. You can also find me here: ...

Live Dev - PufferLib is Fixing Reinforcement Learning

Live Dev - PufferLib is Fixing Reinforcement Learning

Follow jsuarez5341 on X Star https://github.com/pufferai/

How Speeding Up RL Led to Pufferlib (4.8K Stars) |  with Joseph Suarez

How Speeding Up RL Led to Pufferlib (4.8K Stars) | with Joseph Suarez

You might have heard of

The Full Reinforcement Learning Iceberg

The Full Reinforcement Learning Iceberg

Dive into 10 levels of the RL stack with Joseph Suarez, a newly minted MIT PhD and the creator of Neural MMO +

TSAI Conf London

TSAI Conf London

The teams shipping production AI today are figuring it out in real time. ​On July 23, we're bringing them together in London to ...

RSS 2025 Talk on Def-MARL (Best Student Paper Award)

RSS 2025 Talk on Def-MARL (Best Student Paper Award)

Project Website: https://mit-realm.github.io/def-marl/ Songyuan Zhang's talk at Robotics: Science and Systems

PufferLib 1.0 - Making Reinforcement Learning Play Nice

PufferLib 1.0 - Making Reinforcement Learning Play Nice

Dr. Joseph Suarez, creator of Neural MMO, presents

PufferLib - New frontiers in RL

PufferLib - New frontiers in RL

Watch science advance live! I am an MIT PhD and stream my research on reinforcement learning. You can also find me here: ...