Course dossier
Learn each chapter, work through guided checkpoints, then test recall in the linked quiz.
Progress overview
Estimated quiz time: about 190 minutes, plus guided reading. Progress remains local to this browser.
Chapter learning paths
Question-by-question drill on the AlphaStar paper: the two-phase training pipeline, network architecture, RL update (TD(lambda), V-trace, UPGO, KL), league training with PFSP and exploiters, fairness constraints, and transfer to complex multi-agent systems.
Advanced drill on scaling reinforcement learning: Ray's task/actor/object-store model, RLlib abstractions, actor-learner architectures (A3C, Ape-X, IMPALA, SEED RL, R2D2), synchronous vs asynchronous trade-offs, policy lag, and deployment on Kubernetes.
Umfassender Selbsttest auf Deutsch zu RL-Grundlagen, PPO, AlphaStar und League-Training, verteiltem RL mit Ray/RLlib, MLOps und simulationsbasiertem Lernen.
Comprehensive self-assessment on RL fundamentals, PPO, AlphaStar and league training, distributed RL with Ray/RLlib, MLOps, and simulation-based learning.