My solutions to Yandex Practical Reinforcement Learning course in PyTorch and Tensorflow
A course on reinforcement learning in the wild. Taught on-campus at HSE and YSDA and maintained to be friendly to online students (both english and russian).
The syllabus is approximate: the lectures may occur in a slightly different order and some topics may end up taking two weeks.
week1 RL as blackbox optimization
week2 Value-based methods
week3 Model-free reinforcement learning
week4_recap - deep learning recap
week4 Approximate reinforcement learning
week5 Exploration in reinforcement learning
Lecture: Contextual bandits. Thompson Sampling, UCB, bayesian UCB. Exploration in model-based RL, MCTS. "Deep" heuristics for exploration.
Seminar: bayesian exploration for contextual bandits. UCB for MCTS.
** YSDA Deadline: 2018.03.30 23.30**
week6 Policy gradient methods I
week7_recap Recurrent neural networks recap
week7 Partially observable MDPs
week8 Applications II
week9 Policy gradient methods II
Course materials and teaching by: [unordered]