Reinforcement Learning without Verifiable Rewards

Official Schedule Context

Official Description

Verifiable rewards are the gold standard for RL training, but real-world agent tasks frequently lack

clean deterministic evaluation objectives. This talk surveys our efforts to scale RL in non-

verifiable settings -- including task synthesis, unsupervised environment design, and automatic

judge calibration -- to ultimately enable self-improvement in production, grounded in real-world

agent traces and domain-specific context.

Related YouTube Video

Reinforcement Learning for Agents - Will Brown, ML Researcher at Morgan Stanley (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

Transcript Status

Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.

People

Notes

Supporting Slides

Slide Evidence