Scaling Batch Size: Deep Networks Unlock New RL Potential

Hinzugefügt: 2026-05-16

[00:00:00]We actually find that you know, perhaps one hypothesis might be like perhaps the reason why scaling batches isn't that effective in traditional RL because like we've been using these tiny networks that haven't been able to capture that. And one of our experiments is that like because we are enabled successful training of deep network, we actually were able to this is a great test bed for you know, like testing this hypothesis and we find that indeed as we scale the network capacity, we also unlock this different dimension of scaling batch size.