Alignment & Preference Learning · 2017
Deep Reinforcement Learning from Human Preferences
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
Applies toEvidence: Direct
Learning to Summarize from Human Feedback
Preference-RL applied to language summarization
P-201
Source record
Provenance
- Record ID
- P-200
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/1706.03741
- arXiv:1706.03741
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.