DeepMind Control Suite · HackerPapers discussions

DeepMind Control Suite — mentioned by vladf

Thu, 12 May 2022 17:26:38 GMT

This work has two really interesting contributions, in my opinion. 1. Creating a few data points (3) for scaling laws (Figure 8). These behave similar to language models, as gwern puts it [1], but across three data points, it's a bit tough to draw a power-law conclusion (eyeballing the figure, they increase params 4.5x and 3.2x and see about 20% relative performance improvement from each jump). 2. What I find more interesting than the scaling is the out-of-distribution (OOD) generalization results (Figure 9). They test the performance of the agent on a completely unseen task (though possibly…

Paper and discussion history. A mention is not an endorsement.

DeepMind Control Suite — HN submission

Sat, 13 Jan 2018 13:48:56 GMT

DeepMind Control Suite

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

DeepMind Control Suite — HN submission

Thu, 04 Jan 2018 09:29:53 GMT

DeepMind Control Suite

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.