AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning.
Michaël MathieuSherjil OzairSrivatsan SrinivasanÇaglar GülçehreShangtong ZhangRay JiangTom Le PaineRichard PowellKonrad ZolnaJulian SchrittwieserDavid H. ChoiPetko GeorgievDaniel ToyamaAja HuangRoman RingIgor BabuschkinTimo EwaldsMahyar BordbarSarah HendersonSergio Gómez ColmenarejoAäron van den OordWojciech Marian CzarneckiNando de FreitasOriol VinyalsPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- real time
- small scale
- function approximation
- real life
- real world
- machine learning
- markov decision processes
- dynamic programming
- state space
- model free
- optimal policy
- supervised learning
- learning process
- expert systems
- learning environment
- multiscale
- temporal difference
- reinforcement learning algorithms
- control problems
- robotic control