Deep reinforcement learning from human preferences: the abstract says the approach solved complex tasks, including Atari games, from human preferences between pairs of trajectory segments, with feedback on less than one percent of the agent’s interactions with its environment.

The exact words it rests on

In this work, we explore goals defined in terms of (non-expert) human preferences between pairs of trajectory segments. We show that this approach can effectively solve complex RL tasks without access to the reward function, including Atari games and simulated robot locomotion, while providing feedback on less than one percent of our agent's interactions with the environment.

What the source said when we opened it, on 13 Oct 2026.

The source

Deep reinforcement learning from human preferences (arXiv 1706.03741)
arXiv · 2017-06-12

Open the sourcearchived copy

Checked

Checked by the notis newsroom on 13 Oct 2026, against the source above.

In the story

Dario Amodei wants outside testers inside frontier AI companies 14 Oct 2026