63 | ML 6: Characterizations of Federated LearningPublished onDecember 12, 2024 ∘ ~21 mins ∘ ––– viewsmachine-learningreinforcement-learningDigest from a paper presented at NeurIPS '24
38 | ML 5: If My Mother Had Wheels She Would Have Been a Markov Chain Language ModelPublished onJune 5, 2022 ∘ ~28 mins ∘ ––– viewsmachine-learninglinear-algebraReject modernity (transformers); embrace tradition (markov chains)
21 | ML 4: Kit & KaboodlePublished onJune 26, 2020 ∘ ~182 mins ∘ ––– viewsmachine-learningreinforcement-learningSutton, Barto, Bhoag
16 | ML 3.5: A Post by Peter?Published onAugust 1, 2019 ∘ ~5 mins ∘ ––– viewsmachine-learningThis text was generated by a rnn with 700 hidden nodes across 4 layers trained on everything I've has ever written over 500 epochs
14 | ML 3: A Summary of a Summary: DQN BottlenecksPublished onJuly 26, 2019 ∘ ~5 mins ∘ ––– viewsmachine-learningreinforcement-learningRL + Sergey Levine + Swords!
11 | ML 2: A Discussion of Action SpacesPublished onJune 27, 2019 ∘ ~3 mins ∘ ––– viewsmachine-learningreinforcement-learningJust dumb enough that it might work
10 | ML 1: Reinforcement Learning, So Hot Right NowPublished onJune 26, 2019 ∘ ~12 mins ∘ ––– viewsmachine-learningreinforcement-learningOverview of a Summary of Reinforcement Learning