Stanfordの学部レベルの確率統計の授業で使われているonline textbook「The Art of Chance」。証明は略されていないし,それより目を引くのは至るところにRコードが置かれていて,Run Codeをクリックすると計算が実行されたり,グラフが描かれる。どんな仕組みなのだろう?
https://t.co/gIyLNF7MU3
Like Chinchilla, embodied agent research also needs a ton of diverse data to scale. An agent generates its own experience data via interaction & exploration. Its abilities are upper-bounded by the simulator complexity. ProcTHOR offers a scalable way to enrich the experience 3.2/
ProcTHOR: Large-Scale Embodied AI Using Procedural Generation. Deitke et al, @allen_ai. TLDR: ProcTHOR is a simulator that procedurally generates a large variety of interactive, customizable, and physics-enabled houses for training embodied agents. Huge open asset library! 3.1/
NAIST DSC サマーセミナー2022の講演資料を公開しました。Transformerと基盤モデルの話を中心に据えました。(Diffusionなtext-to-imageの技術的な話はしてないので悪しからず・・・)
2022.9.7 NAIST DSCサマーセミナー「Vision and Language技術の最新動向」 https://t.co/RB9QXzrbeX
Training RL from scratch can be very hard, if there is any prior policy you can use to help, you should.
But using prior policies with value-based RL is difficult for various RL reasons.
Introducing Jump-Start RL: a simple, widely applicable method that addresses this problem.