Reinforcement Learning

65 readers

1 users here now

A community dedicated to discussions on reinforcement learning, a subdiscipline of machine learning that tackles sequential decision making problems.

founded 2 years ago

MODERATORS

howrar@lemmy.ca

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks (arxiv.org)

submitted 3 months ago by howrar@lemmy.ca to c/reinforcement_learning@lemmy.ca

2 comments fedilink hide all child comments

RL is still nowhere near the scale where this matters, but it's always good to get an idea of how things are going to look when they inevitably reach that point.

top 2 comments

sorted by: hot top controversial new old

[–] howrar@lemmy.ca 1 points 3 months ago

One thing that stood out to me was that none of their agents performed well on boxing or pong, but in my experience, these are the two easiest tasks in the entire Atari suite. They're the games I use as quick sanity checks. How did they manage that?

[–] bear@lemmy.blahaj.zone 1 points 2 months ago

I heard that AI training is already releasing as much carbon dioxide as airplanes.