Joseph Suarez 🐡's banner

Joseph Suarez 🐡

@jsuarez • 31,356 subscribers

I build sane open-source RL tools. MIT PhD, creator of Neural MMO and founder of PufferAI. DM for business: non-LLM sim engineering, RL R&D, infra & support.

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Releasing PufferLib 5.0: Train agents in under a second

Releasing PufferLib 5.0: Train agents in under a second

Joseph Suarez 🐡

170,065 просмотров • 1 месяц назад

You can train drones in 30 seconds. This was a year ago. PufferLib is 5x faster now!

You can train drones in 30 seconds. This was a year ago. PufferLib is 5x faster now!

Joseph Suarez 🐡

161,845 просмотров • 4 месяцев назад

Releasing PufferLib 4.0: Train agents in seconds

Releasing PufferLib 4.0: Train agents in seconds

Joseph Suarez 🐡

216,829 просмотров • 6 месяцев назад

RL really sucks. It takes 10 hours just to learn breakout. ... a few years ago. It's <30 seconds on 1 GPU now in PufferLib and still dropping. Write faster code.

RL really sucks. It takes 10 hours just to learn breakout. ... a few years ago. It's <30 seconds on 1 GPU now in PufferLib and still dropping. Write faster code.

Joseph Suarez 🐡

267,754 просмотров • 1 год назад

PufferLib 3.0: We trained reinforcement learning agents on 1 Petabyte / 12,000 years of data with 1 server. Now you can, too! Our latest release includes algorithmic breakthroughs, massively faster training, and 10 new environments. Live demos on our site. Volume on for trailer!

PufferLib 3.0: We trained reinforcement learning agents on 1 Petabyte / 12,000 years of data with 1 server. Now you can, too! Our latest release includes algorithmic breakthroughs, massively faster training, and 10 new environments. Live demos on our site. Volume on for trailer!

Joseph Suarez 🐡

194,767 просмотров • 1 год назад

My thesis has been accepted - 170 pages of Neural MMO available on my github io (jsuarez5341). Thank you to my advisor Phillip Isola, my committee Pulkit Agrawal Eugene Vinitsky 🦋, and my parents Jose and Patricia Suarez, to whom I devote my thesis.

My thesis has been accepted - 170 pages of Neural MMO available on my github io (jsuarez5341). Thank you to my advisor Phillip Isola, my committee Pulkit Agrawal Eugene Vinitsky 🦋, and my parents Jose and Patricia Suarez, to whom I devote my thesis.

Joseph Suarez 🐡

53,752 просмотров • 2 лет назад

Reinforcement Learning 10,000x Faster - an invited talk for the University of Warwick's AI summit. I share the story of Neural MMO and how a crazy out-there MMO AI project became the basis for PufferLib, the fastest RL library available today. Star puffer on github to support!

Reinforcement Learning 10,000x Faster - an invited talk for the University of Warwick's AI summit. I share the story of Neural MMO and how a crazy out-there MMO AI project became the basis for PufferLib, the fastest RL library available today. Star puffer on github to support!

Joseph Suarez 🐡

16,994 просмотров • 7 месяцев назад

Больше нет контента для загрузки