Alignment & Preference Learning · 2017

Deep Reinforcement Learning from Human Preferences

Paul Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, Dario Amodei

Showed a reward model can be trained from humans' pairwise comparisons of agent trajectory segments, letting RL optimize behaviors too hard to hand-specify without ever writing an explicit reward function.

Editorial record

Plain-language summary

The work has people repeatedly pick which of two short video clips of an agent looks closer to a goal, and fits a reward predictor to those choices while a policy is trained against that predictor. Because labeling comparisons is cheaper than demonstrating or coding rewards, it learned tasks like Atari games and simulated-robot backflips from under an hour of human feedback on a small fraction of the agent's interactions. This comparison-based reward modeling became the template later scaled to language-model alignment.

Knowledge graph

Relationships

Antecedents

Source record

Provenance

Record ID
P-200
Record created
2026-07-13
Last reviewed
2026-07-14
Record version
2

Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.