News for hackers. Stuff that matters.
Re:Q-learning is not yet scalable by highd on Sunday June 15, 2025 @02:27PM (#44284057)
You can do Q-Learning with a transformer. You simply define the state space as the observation sequence. This is in fact natural to do in partially observed settings. So your distinction does not make sense.
Re:Q-learning is not yet scalable by isaacimagine on Sunday June 15, 2025 @02:51PM (#44284217)
DT's reward-to-go vs. QL's Bellman incl. discount, not choice of architecture for policy. You could also do DTs with RNNs (though own problems w/ memory).

Apologies if we're talking past one another.