RB

Replay buffers in reinforcement learning

Topic

Expert statements

1
1 positive

What experts have said about Replay buffers in reinforcement learning

1 statement · 1 positive

  1. Eric JangPositiveMay 15, 2026· Dwarkesh Podcast

    Replay buffers should contain on-policy states plus off-policy recovery states.

    “your replay buffer really should have the states that your policy would visit, plus some distribution of states that you might drift to and then how to return back to your optimal states”

    Listen at 2:04:31

    Open the episode · Eric Jang – Building AlphaGo from scratch
Filter the statements →

Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.

Replay buffers in reinforcement learning · PodLume