long-horizon RL
Reinforcement learning aimed at training models to carry out long, multi-step tasks or projects coherently rather than single steps.
As defined in John Schulman (OpenAI Cofounder) — Reasoning, RLHF, & plan for 2027 AGI
Where it comes up · 1
Most important claims · 2 of 2Search all claims for “long-horizon RL” →
- Near-term capability gains will come from training models to carry out longer, more involved projects (e.g. an entire coding project: writing files, testing, iterating) rather than single steps, and because this training area is new there is a lot of low-hanging fruit in it.John Schulman (OpenAI Cofounder) — Reasoning, RLHF, & plan for 2027 AGI
- The mental model of AI will shift from one-off search-engine-like queries toward a helpful colleague that shares a whole ongoing project, knows everything you've done on it, proactively makes suggestions, remembers to follow up, and works in the background—with form factors (e.g. a Clippy on your computer vs a cloud colleague) still to be determined.John Schulman (OpenAI Cofounder) — Reasoning, RLHF, & plan for 2027 AGI