Benjamin Eysenbach

Assistant Professor of Computer Science, Princeton University · 1 appearance on the record.

computed by AI from the episodes · how this works → · full disclaimer →

academicscientist@ben_eysenbach ↗ben-eysenbach.github.io ↗

He leads the Princeton Reinforcement Learning Lab, researching self-supervised control, autonomous exploration, and scalable reinforcement learning algorithms. Prior to Princeton, he conducted research at Google Brain and earned his Ph.D. from Carnegie Mellon University.

3statements → 2claims → 2claims resolved → 4/5average certainty → 2.33/5average debate potential →

2 supported 0 partly supported 0 contradicted how the 2 claims stand · each chip opens the sources

2 assertions · 1 insight · every statement was checked. The predictions and assertions are the 2 claims: statements the public record can support or contradict. 2 are resolved. Everything else (opinions, insights, what ifs, disclosures) can never be settled by the record, so it carries no assessment.

The record, in short

What the tape says about how Benjamin argues and how the claims held up. Everything they said, and everything said about them, is in the tabs below.

Their most notable supported claim

Assertion Supported

Eysenbach: Scaling RL depth requires combining depth with residual connections

“And if we just made the depth bigger, it makes it worse. If we just add residual connections, it didn't make it better. And it was really this combination of factors that Kevin and Ishan figured out that really made this work.”

Benjamin Eysenbach Dec 31, 2025 ▶ 5:56 [NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised RL — Kevin Wang et al, Princeton

What they said3 Episodes1

Everything Benjamin Eysenbach said on Latent Space that made the record, most notable first. Filter by type, assessment or year in the ledger →

Insight

Eysenbach: 1,000-layer RL requires reward-free objectives, not just architectural tricks

“I think the main conclusion is that using big networks not only requires these architectural tricks, but also, as Kevin mentioned before, it requires using a different objective. This objective doesn't actually use rewards in it, and so there's another word in…”

Benjamin Eysenbach Dec 31, 2025 ▶ 8:08 [NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised RL — Kevin Wang et al, Princeton

Assertion Supported

Eysenbach: Scaling RL depth requires combining depth with residual connections

Benjamin Eysenbach Dec 31, 2025 ▶ 5:56 [NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised RL — Kevin Wang et al, Princeton

Assertion Supported

Eysenbach: Historically, 'deep' RL meant only two to four layers

“So it's like, probably my lab works on deep reinforcement learning, but historically deep meant like two or three or four layers.”

Benjamin Eysenbach Dec 31, 2025 ▶ 2:15 [NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised RL — Kevin Wang et al, Princeton

Appearances (1)

Episode	Date	Speaking time
[NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised RL — Kevin Wang et al, Prince	Dec 31, 2025	2m

Benjamin Eysenbach

The record, in short

Their most notable supported claim

Appearances (1)

Turn any episode into a week of clips.